© 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. 126502
    Prev
    Next
    INDEX
    Explanations

    writing or recommending graduation

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

    altered

    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
     infiltrate
    0.49
     تجاه
    0.43
    VN
    0.39
    NETWORK
    0.39
     hijos
    0.39
    巡
    0.39
    گن
    0.38
     ে
    0.38
     inland
    0.37
     infil
    0.37
    POSITIVE LOGITS
     respectivement
    0.52
    😚
    0.49
    🧉
    0.49
     Ngày
    0.48
     waktu
    0.47
     Nikhil
    0.47
    pyrid
    0.46
    üssel
    0.46
    دید
    0.46
    ારીખ
    0.46
    Activations Density 0.000%

    No Known Activations