© 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. 102581
    Prev
    Next
    INDEX
    Explanations

    numbers and zip codes

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

    describing problems and consequences

    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
     infecting
    0.52
     (
    0.50
    ;
    0.45
     infections
    0.45
     України
    0.45
     dancers
    0.44
    [
    0.43
     lệch
    0.43
    फ्रेंस
    0.43
     danced
    0.42
    POSITIVE LOGITS
     ಸ್ಥಳ
    0.53
    锶
    0.53
    protein
    0.50
    ן
    0.50
    ㎿
    0.50
    mRNA
    0.48
     svojoj
    0.48
    than
    0.46
    MATRIX
    0.46
    BUND
    0.46
    Activations Density 0.001%

    No Known Activations