© 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. 244362
    Prev
    Next
    INDEX
    Explanations

    consent, permission, agreement

    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
    文
    0.51
    스
    0.49
     लड़की
    0.48
    䝬
    0.48
    ುನ
    0.48
    لیک
    0.47
    影子
    0.47
    भा
    0.46
    جاد
    0.46
    竺
    0.46
    POSITIVE LOGITS
     fits
    0.52
     Бар
    0.48
     x
    0.47
    rometry
    0.47
     pliers
    0.46
     empfohlen
    0.45
    quête
    0.45
     Kay
    0.42
     Seiten
    0.42
     tég
    0.42
    Activations Density 0.001%

    No Known Activations