© 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. 35667
    Prev
    Next
    INDEX
    Explanations

    large number, Supreme Court, and right

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

    experience, health, safety, SQL

    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
    founded
    0.49
    ↵
    0.48
     receive
    0.45
     pesky
    0.45
    ผ
    0.45
     capabilities
    0.44
     lance
    0.44
    는
    0.44
     Davey
    0.43
     nutrients
    0.43
    POSITIVE LOGITS
     μαύ
    0.50
     फिल्मी
    0.48
     multiSelectList
    0.48
     accanto
    0.47
    ℍ
    0.47
    訸
    0.46
     opini
    0.46
     সড়ক
    0.46
     δύο
    0.45
    λούν
    0.45
    Activations Density 0.000%

    No Known Activations