© 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. 148027
    Prev
    Next
    INDEX
    Explanations

    appraisal

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

    immigration and nationality act

    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
     trivial
    0.50
     تربیت
    0.47
     $
    0.46
    וד
    0.46
     messages
    0.46
    rivial
    0.43
    od
    0.43
    ów
    0.43
     VPS
    0.42
     disseminating
    0.42
    POSITIVE LOGITS
    arote
    0.59
    仴
    0.55
    ્યાર
    0.55
    Callories
    0.54
     гель
    0.53
     indah
    0.52
    ︵
    0.52
    ImageAsset
    0.51
    ChessBot
    0.50
    PHIL
    0.50
    Activations Density 0.001%

    No Known Activations