© 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. 14364
    Prev
    Next
    INDEX
    Explanations

    you need / cult of

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

    key figures in philosophy

    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
     unspoken
    0.51
    .
    0.50
     academy
    0.50
     ba
    0.48
     aujourd
    0.46
    zare
    0.46
    在这
    0.44
    etra
    0.44
     siy
    0.44
     faculty
    0.43
    POSITIVE LOGITS
     fringes
    0.51
     cellulose
    0.48
    ينات
    0.46
    詑
    0.46
    హం
    0.46
     বাঙালিদের
    0.46
    覀
    0.46
     मिळते
    0.45
     Cellulose
    0.45
     bactéries
    0.45
    Activations Density 0.000%

    No Known Activations