© 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. 177245
    Prev
    Next
    INDEX
    Explanations

    dumpsters offer

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

    be specific, define metrics, find problems

    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
    ırmaya
    0.45
     Armor
    0.42
    śli
    0.41
     armor
    0.41
     Syntax
    0.41
     Dessa
    0.40
    orable
    0.40
    痧
    0.40
     confusing
    0.39
     authorize
    0.39
    POSITIVE LOGITS
    ьев
    0.50
    čen
    0.50
    НИ
    0.48
    PARENT
    0.45
    nytimes
    0.45
    cares
    0.45
     недели
    0.45
     мину
    0.43
     چه
    0.43
    AVER
    0.43
    Activations Density 0.000%

    No Known Activations