© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 104679
    Prev
    Next
    INDEX
    Explanations

    Category: players

    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
     válvula
    -1.02
    不可思议
    -0.98
    回来了
    -0.98
     instead
    -0.96
     needing
    -0.93
    괜
    -0.93
     cáps
    -0.93
     expérience
    -0.92
     выбирать
    -0.92
    ofas
    -0.91
    POSITIVE LOGITS
     动画
    1.02
    一般的な
    1.00
     ilustrasi
    0.99
     Presumably
    0.97
    //!
    0.96
     duża
    0.96
     Также
    0.91
     sosok
    0.89
     ہیں۔
    0.89
     idyllic
    0.88
    Activations Density 0.087%

    No Known Activations