© 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. 10542
    Prev
    Next
    INDEX
    Explanations

    assignment of booleans or identifiers

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

    conditional logic and error handling

    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
     structs
    0.20
     L
    0.20
     strawberries
    0.20
    =
    0.19
    =[
    0.19
    struct
    0.19
     berries
    0.19
     enzyme
    0.19
     polynomials
    0.19
     d
    0.19
    POSITIVE LOGITS
    IsNot
    0.19
     !_
    0.19
     не
    0.19
     일이
    0.18
     !$
    0.18
     כאשר
    0.18
     परिस्थितीत
    0.18
     didn
    0.17
    ነው
    0.17
     ikke
    0.17
    Activations Density 0.000%

    No Known Activations