Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7856
    Prev
    Next
    INDEX
    Explanations

    years or numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     a
    -1.41
     of
    -1.31
    P
    -1.30
     ২০১
    -1.23
     You
    -1.23
    S
    -1.23
    “
    -1.18
     I
    -1.16
     has
    -1.16
     P
    -1.14
    POSITIVE LOGITS
    ränken
    1.49
     italiens
    1.36
    Vegeta
    1.30
     chrétien
    1.29
    <bos>
    1.29
    struzioni
    1.27
     bré
    1.27
     trente
    1.27
     huile
    1.26
    Ár
    1.26
    Activations Density 0.120%

    No Known Activations