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. 7965
    Prev
    Next
    INDEX
    Explanations

    Case in, once in

    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
     calefacción
    -1.05
     respiración
    -0.90
    mici
    -0.90
     Invocation
    -0.89
    inches
    -0.89
     personalización
    -0.88
     любую
    -0.86
    Inches
    -0.82
     PREFIX
    -0.80
    Dans
    -0.79
    POSITIVE LOGITS
     in
    3.86
     In
    1.75
    In
    1.23
    in
    1.19
     în
    1.17
     در
    1.16
     IN
    0.98
     σε
    0.93
     and
    0.88
    insegna
    0.87
    Activations Density 0.017%

    No Known Activations