© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 84142
    Prev
    Next
    INDEX
    Explanations

    bracketed or punctuated phrases

    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
     and
    -1.81
    '
    -1.76
     videojuegos
    -1.73
    那位
    -1.66
     persoons
    -1.60
    section
    -1.59
    --
    -1.59
     вашего
    -1.58
    0
    -1.58
     "
    -1.57
    POSITIVE LOGITS
    咴
    2.13
    ㉗
    1.98
    accéder
    1.98
    妡
    1.91
    𓆟
    1.88
     a
    1.83
    ㉖
    1.73
    我现在
    1.73
     owing
    1.72
    瑒
    1.70
    Activations Density 0.010%

    No Known Activations