© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 7188
    Prev
    Next
    INDEX
    Explanations

    Mo/Mod prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mati
    0.95
     homicide
    0.94
     món
    0.92
     intermission
    0.89
     manner
    0.89
     moyen
    0.84
     mortality
    0.83
    耆
    0.82
     melted
    0.82
     Stateful
    0.81
    POSITIVE LOGITS
    バイル
    1.50
    挲
    1.47
    ambique
    1.37
    ammed
    1.35
    ality
    1.31
    anwhile
    1.30
    gomery
    1.29
    ivated
    1.21
    바일
    1.21
    emploi
    1.20
    Activations Density 0.389%

    No Known Activations