© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108742
    Prev
    Next
    INDEX
    Explanations

    words starting with th

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates strongly on any token fragment containing the letter sequence “th” (in any case).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the substring "th" appearing in various contexts, particularly in proper nouns, technical terms, and non-English words.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    occurrences of the letter sequence “th” (any casing), especially at the start of a word or morpheme.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     biber
    -0.81
    printable
    -0.79
     Akk
    -0.79
    olto
    -0.76
    MER
    -0.74
    quila
    -0.73
    beruf
    -0.73
    HER
    -0.73
    ști
    -0.72
     offici
    -0.72
    POSITIVE LOGITS
     often
    1.11
     sometimes
    0.98
     Often
    0.97
     Sometimes
    0.90
    Sometimes
    0.83
     frequently
    0.82
     assoluto
    0.81
     Messiah
    0.80
     Kaduna
    0.79
     usually
    0.79
    Activations Density 0.004%

    No Known Activations