© 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. 22339
    Prev
    Next
    INDEX
    Explanations

    carp fishing

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

    DB and array formulas

    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
     impuestos
    0.51
     税
    0.50
     exper
    0.49
     അനു
    0.48
     ADS
    0.48
     anon
    0.48
     ANON
    0.48
     Hegel
    0.47
     RxSwift
    0.46
     entitlements
    0.46
    POSITIVE LOGITS
    ২০
    0.54
    シャー
    0.53
    ๗
    0.52
    綻
    0.49
    ر
    0.49
    ἂ
    0.49
    ศ
    0.49
    らん
    0.47
    滅
    0.47
    дной
    0.47
    Activations Density 0.000%

    No Known Activations