© 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. 212511
    Prev
    Next
    INDEX
    Explanations

    blocking conception

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

    dictionary definitions `{}`

    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
     toast
    0.50
     (
    0.49
     responder
    0.48
     battle
    0.46
     black
    0.45
     spot
    0.44
     guard
    0.44
     fledgling
    0.44
     core
    0.44
    day
    0.43
    POSITIVE LOGITS
     而且
    0.61
    𝘭
    0.56
    舢
    0.55
     COMPOUNDS
    0.55
     ហើយ
    0.54
     електро
    0.54
     கு
    0.53
    㛣
    0.53
     उत्सर्जन
    0.52
     會
    0.52
    Activations Density 0.000%

    No Known Activations