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. 8629
    Prev
    Next
    INDEX
    Explanations

    by induction

    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
    junit
    -0.81
    uría
    -0.76
     ź
    -0.76
     famiglia
    -0.73
     tega
    -0.73
     dazzling
    -0.73
     precioso
    -0.73
    prez
    -0.72
    ++$
    -0.71
     jūs
    -0.71
    POSITIVE LOGITS
     absurd
    0.94
     dismal
    0.90
     cạnh
    0.88
     tinha
    0.83
    volving
    0.82
    ifoli
    0.81
    ;'>
    0.80
     apply
    0.79
    ोन
    0.79
    TableId
    0.79
    Activations Density 0.002%

    No Known Activations