© 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. 74320
    Prev
    Next
    INDEX
    Explanations

    Alexander the Great; restored; bizarre

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

    suppression of dissent

    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
     чыныгы
    0.50
     useCallback
    0.50
     মানে
    0.49
    ধু
    0.47
    א
    0.46
    マル
    0.45
    फु
    0.45
     બ
    0.44
    attamente
    0.44
     değil
    0.44
    POSITIVE LOGITS
     इच्छ
    0.49
     क्लो
    0.48
     Gestaltung
    0.48
     Punkt
    0.48
     Chargers
    0.48
     Leistungen
    0.48
     Änderung
    0.47
     Ét
    0.47
    xiv
    0.46
     reinstatement
    0.46
    Activations Density 0.001%

    No Known Activations