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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60588
    Prev
    Next
    INDEX
    Explanations

    special characters or start of sentence

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

    The neuron strongly responds to non‐letter tokens—especially punctuation marks (periods, commas, exclamation points) and standalone numbers.

    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
    ったのは
    -1.12
    はこの
    -1.12
     idiota
    -1.05
    腭
    -1.03
     они
    -0.98
    Ḿ
    -0.98
     océ
    -0.96
     tendre
    -0.93
     it
    -0.93
    кульп
    -0.93
    POSITIVE LOGITS
     whether
    2.44
     Whether
    2.02
     with
    1.96
    Whether
    1.88
     you
    1.78
     your
    1.69
     whatever
    1.61
    whether
    1.61
     from
    1.59
     contact
    1.56
    Activations Density 0.077%

    No Known Activations