© 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. 173742
    Prev
    Next
    INDEX
    Explanations

    email update

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

    enforces integrity or rules

    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
     bunlar
    0.46
     हाइड्रोजन
    0.46
    crast
    0.45
    \}}\
    0.45
     இவற்றை
    0.43
     لي
    0.43
    쁨
    0.43
     Wikiped
    0.42
     استخدم
    0.42
     섹
    0.42
    POSITIVE LOGITS
     unique
    0.49
     nya
    0.48
     NCR
    0.48
     Gis
    0.47
     saab
    0.47
     Global
    0.45
     Seu
    0.44
     pintu
    0.44
     únicas
    0.43
    KER
    0.43
    Activations Density 0.001%

    No Known Activations