© 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. 223572
    Prev
    Next
    INDEX
    Explanations

    withdrawal, returns, monthly, Japan, Keto

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

    Multi-Role capability

    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
    ucks
    0.39
    ♈
    0.39
    xk
    0.37
    loin
    0.37
    loving
    0.36
    ال
    0.36
    zol
    0.36
    햄
    0.36
    bright
    0.35
    adjusted
    0.35
    POSITIVE LOGITS
     theseKeys
    0.56
     precludes
    0.55
     vVertex
    0.53
     其
    0.52
     boat
    0.50
     vessel
    0.50
     treb
    0.50
    дія
    0.49
     модерни
    0.49
     фаразы
    0.48
    Activations Density 0.001%

    No Known Activations