© 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. 46638
    Prev
    Next
    INDEX
    Explanations

    fled the capital

    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
    タイム
    0.40
    ich
    0.40
    den
    0.40
    Wm
    0.40
    ্ক
    0.40
    業界
    0.40
    🍷
    0.39
    ิบ
    0.39
     Nasdaq
    0.39
    ùi
    0.38
    POSITIVE LOGITS
     EARLY
    0.44
     broadening
    0.43
     surveillance
    0.42
     intervening
    0.41
     influencing
    0.41
     logros
    0.41
     programas
    0.40
     vajj
    0.39
     dirige
    0.39
     REPORTS
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.