© 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. 10013
    Prev
    Next
    INDEX
    Explanations

    presentation, poly, provide

    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
     fisc
    0.52
    WIT
    0.49
    ナ
    0.49
    禰
    0.48
    翳
    0.47
    4
    0.47
    iae
    0.46
    hoea
    0.45
    \%
    0.45
    瘡
    0.45
    POSITIVE LOGITS
     OBJ
    0.55
     bodysuit
    0.52
     EVENT
    0.51
     dehyd
    0.50
     DEL
    0.48
     defibr
    0.48
     Objekt
    0.48
     putty
    0.47
     fluores
    0.47
     방문
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.