© 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. 21857
    Prev
    Next
    INDEX
    Explanations

    asking about what's best

    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
     Ability
    0.46
     gxh
    0.42
     Allows
    0.42
    Allows
    0.41
    Able
    0.41
    Ability
    0.40
    𓈒
    0.40
     (__
    0.40
    可以让
    0.40
     Familiar
    0.40
    POSITIVE LOGITS
     escolas
    0.47
     škola
    0.42
     schools
    0.42
     escuelas
    0.41
     samb
    0.40
     dressings
    0.39
     dressing
    0.39
     escola
    0.39
    ؤول
    0.39
     pesquisas
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.