© 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. 83644
    Prev
    Next
    INDEX
    Explanations

    aware, very, request, donations

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

    reporting issues, meals, results

    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
     A
    0.47
     Oh
    0.46
     England
    0.44
    oken
    0.43
    BD
    0.42
    estation
    0.41
     Rotor
    0.41
     was
    0.40
     Oppen
    0.40
     duties
    0.39
    POSITIVE LOGITS
    𒌨
    0.50
     farce
    0.50
    osť
    0.48
    indruck
    0.47
    場所
    0.46
    綏
    0.46
    競技
    0.46
     જોડ
    0.46
    崛起
    0.46
    unky
    0.46
    Activations Density 0.000%

    No Known Activations