© 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. 134947
    Prev
    Next
    INDEX
    Explanations

    2 animal crossing

    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
     Champion
    0.48
     Éd
    0.46
    乡
    0.45
     Compan
    0.45
     Drought
    0.44
     orphaned
    0.43
     ép
    0.42
     গেল
    0.42
     Perpet
    0.41
    毂
    0.41
    POSITIVE LOGITS
    enci
    0.50
    isdigit
    0.50
    צי
    0.50
     improves
    0.48
    iod
    0.46
    correlation
    0.46
    chemin
    0.46
     효율
    0.45
     합동
    0.45
     및
    0.44
    Activations Density 0.000%

    No Known Activations