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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39915
    Prev
    Next
    INDEX
    Explanations

    list of items

    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_10/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
    ⚣
    -2.47
    臜
    -2.30
    {
    -2.08
    這一
    -2.03
    鲩
    -1.92
    诓
    -1.85
     ไม่
    -1.84
    鲥
    -1.79
    𨭆
    -1.77
    🪤
    -1.76
    POSITIVE LOGITS
    轵
    2.72
    !"
    2.63
    “
    2.44
    !!!"
    2.16
    ?"
    2.13
    ليات
    1.96
    焄
    1.91
     collaboration
    1.87
    ficas
    1.84
    …"
    1.84
    Activations Density 0.018%

    No Known Activations