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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90095
    Prev
    Next
    INDEX
    Explanations

    first followed by of or off

    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
    ariats
    -1.08
     bytu
    -1.00
    muerzo
    -0.97
    所在
    -0.96
     ganska
    -0.94
    ватися
    -0.93
     gemeenten
    -0.91
    жением
    -0.90
    さまざま
    -0.90
    ソッド
    -0.89
    POSITIVE LOGITS
     of
    4.88
     off
    2.23
    Of
    1.70
    of
    1.63
     Of
    1.53
    ,
    1.47
    ของ
    1.42
     конечно
    1.30
    もちろん
    1.30
    当然
    1.23
    Activations Density 0.019%

    No Known Activations