© 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. 242178
    Prev
    Next
    INDEX
    Explanations

    songs, Desk, Lake Tahoe, Greatest

    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
     يساعد
    0.53
    eid
    0.50
    ͋
    0.49
    mdui
    0.49
    model
    0.48
    getHours
    0.48
    xlim
    0.47
    serv
    0.47
     ير
    0.47
    ret
    0.47
    POSITIVE LOGITS
     Feather
    0.52
    cence
    0.52
     कोण
    0.52
     goat
    0.50
     sanitation
    0.47
     Minority
    0.47
     feather
    0.46
     छ
    0.46
    Bez
    0.46
     Sin
    0.45
    Activations Density 0.000%

    No Known Activations