© 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. 210785
    Prev
    Next
    INDEX
    Explanations

    phrases describing properties or consequences

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

    compile time constants

    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
    غت
    0.44
     shoved
    0.41
    0.40
    साइ
    0.39
     "";
    0.39
     instincts
    0.39
    ;")
    0.38
    iclopedia
    0.38
    马克
    0.38
     '';
    0.38
    POSITIVE LOGITS
    cidr
    0.55
     каталог
    0.54
    catalog
    0.54
    ))(
    0.52
     символ
    0.52
    executable
    0.51
    кара
    0.51
    BTC
    0.50
    medic
    0.50
    тун
    0.50
    Activations Density 0.000%

    No Known Activations