© 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. 64338
    Prev
    Next
    INDEX
    Explanations

    events, locations, and roles

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

    political landscape and transition

    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
    ?!?
    0.64
     That
    0.59
    ?!?!
    0.58
    ?!
    0.57
     আমাকে
    0.56
     Quiero
    0.56
    آ
    0.56
    ؟
    0.55
     Quelle
    0.52
     నాకు
    0.52
    POSITIVE LOGITS
     विभिन्न
    0.50
     racetr
    0.50
     linemen
    0.46
     mergers
    0.45
     structuring
    0.44
     biomarker
    0.43
     civiles
    0.43
     workspaces
    0.43
     politič
    0.43
     restricts
    0.43
    Activations Density 0.002%

    No Known Activations