© 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. 14699
    Prev
    Next
    INDEX
    Explanations

    authorship information

    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
    谀
    0.43
    Professor
    0.43
     revisar
    0.43
    Aprend
    0.42
    лакти
    0.42
    에서는
    0.42
     Маке
    0.41
    लिए
    0.41
    旲
    0.41
    लिप
    0.41
    POSITIVE LOGITS
    table
    0.53
    r
    0.52
     bubble
    0.44
     နှစ်
    0.44
     jail
    0.44
    tw
    0.44
     booze
    0.44
     dva
    0.43
     Jail
    0.43
    jail
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.