© 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. 9728
    Prev
    Next
    INDEX
    Explanations

    code structure and components

    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
     genetics
    0.43
    τίας
    0.43
     avec
    0.42
     chirality
    0.41
     organis
    0.41
    誡
    0.41
    ᵉ
    0.40
     Son
    0.40
     pulsation
    0.40
    ালিক
    0.39
    POSITIVE LOGITS
    ,,
    0.59
    *,
    0.53
    vaegir
    0.53
    |,
    0.50
    !,
    0.47
     –,
    0.47
    ahasan
    0.45
    judul
    0.45
    chyné
    0.45
    DeleteDialogOpen
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.