© 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. 58385
    Prev
    Next
    INDEX
    Explanations

    guidance provided or needed

    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
    ࣭
    -2.92
    簟
    -2.91
    甞
    -2.86
    ⸒
    -2.70
    鐃
    -2.67
    厖
    -2.58
    鬭
    -2.56
    //'
    -2.50
    鉏
    -2.48
     was
    -2.47
    POSITIVE LOGITS
    .
    3.02
    趼
    2.83
     ferv
    2.75
     of
    2.73
    摭
    2.69
     were
    2.64
    媗
    2.47
    鶿
    2.42
    those
    2.39
    This
    2.38
    Activations Density 0.009%

    No Known Activations