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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109983
    Prev
    Next
    INDEX
    Explanations

    javascript eval execution

    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
    ("<
    -0.84
     Quotes
    -0.79
     incision
    -0.77
    మా
    -0.77
     "<
    -0.77
    總
    -0.76
    `<
    -0.76
    Lambda
    -0.75
     inconn
    -0.75
     `<
    -0.75
    POSITIVE LOGITS
     coment
    0.78
    **.
    0.78
     líneas
    0.77
     priva
    0.75
     lines
    0.75
     preſ
    0.74
     munici
    0.73
     surrendering
    0.73
    ResultCode
    0.73
     commented
    0.73
    Activations Density 0.015%

    No Known Activations