© 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. 91408
    Prev
    Next
    INDEX
    Explanations

    key word or words

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

    The neuron fires on occurrences of the word “key” (as in “Key Words,” “key term,” or similar headings).

    oai_token-act-pair · o4-miniTriggered 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
    cular
    -0.77
     desks
    -0.72
    hift
    -0.68
    IEnumerator
    -0.67
    phism
    -0.67
    Ciao
    -0.66
    ława
    -0.63
    텍
    -0.63
    żd
    -0.63
    ctober
    -0.63
    POSITIVE LOGITS
    word
    3.13
     words
    3.00
    words
    2.92
     word
    2.91
    Words
    2.53
     Words
    2.45
    Word
    2.45
    WORDS
    2.33
    WORD
    2.14
     Word
    1.98
    Activations Density 0.044%

    No Known Activations