© 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. 195499
    Prev
    Next
    INDEX
    Explanations

    reporting statements about people and things

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

    following up

    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
    নকে
    0.52
    斯特
    0.50
     associé
    0.49
    窨
    0.49
     соответствующие
    0.49
     εικό
    0.48
     মুক্তিফৌজ
    0.47
    聪明
    0.47
     μέρος
    0.46
    阱
    0.46
    POSITIVE LOGITS
    0.49
    v
    0.48
     undeniably
    0.48
    ید
    0.45
     monolithic
    0.45
     evergreen
    0.44
    .
    0.44
    the
    0.44
     lifetime
    0.44
    Def
    0.43
    Activations Density 0.000%

    No Known Activations