© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92139
    Prev
    Next
    INDEX
    Explanations

    quantities and completion

    np_acts-logits-general · gemini-2.5-flash-lite

    report, audience, video, explains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UN
    0.52
    TLS
    0.50
    ƙ
    0.49
    DeviceCompliance
    0.49
    Ҷ
    0.47
    ۳
    0.46
    COD
    0.46
    ५
    0.45
    ID
    0.45
    nginx
    0.45
    POSITIVE LOGITS
     herman
    0.50
     pak
    0.48
     pedals
    0.48
     skoro
    0.47
     Gerais
    0.47
     zz
    0.46
     aar
    0.46
     của
    0.46
     ImageView
    0.45
     iw
    0.45
    Activations Density 0.000%

    No Known Activations