© 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. 22-GEMMASCOPE-RES-131K
    4. 291
    Prev
    Next
    INDEX
    Explanations

    going home

    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_22/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
     Dinge
    -0.96
    /**/
    -0.96
    场合
    -0.93
    ous
    -0.93
    ως
    -0.92
    ψ
    -0.89
    مشخص
    -0.89
    درمان
    -0.88
    foto
    -0.88
     hossz
    -0.88
    POSITIVE LOGITS
     home
    1.27
    🏠
    1.04
    vidade
    1.00
    🏡
    0.94
     Comprometido
    0.93
    ඟ
    0.90
    жина
    0.90
     rodzin
    0.90
    cetype
    0.90
    𝔹
    0.89
    Activations Density 0.019%

    No Known Activations