© 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. 24703
    Prev
    Next
    INDEX
    Explanations

    visiting places or activity

    np_acts-logits-general · gemini-2.5-flash-lite

    forbidden, gaps, belonging

    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
    omina
    0.49
    missible
    0.45
    typical
    0.45
    missive
    0.45
    resonant
    0.45
    riera
    0.44
    ;');
    0.44
    ্তা
    0.44
     リボン
    0.44
    <unused619>
    0.44
    POSITIVE LOGITS
     stories
    0.51
     were
    0.50
     ice
    0.48
     Dun
    0.46
     doğrud
    0.45
     конкур
    0.44
     byly
    0.43
    吧
    0.43
     ancestors
    0.43
     halten
    0.43
    Activations Density 0.000%

    No Known Activations