© 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. 62571
    Prev
    Next
    INDEX
    Explanations

    property owned

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

    exploring and fostering cooperation

    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
    Ouest
    0.49
    Lac
    0.46
    لي
    0.45
    МА
    0.44
    Deux
    0.44
    O
    0.44
    ON
    0.44
     Occurrence
    0.44
     Foundation
    0.43
    迭
    0.43
    POSITIVE LOGITS
     spandex
    0.53
     使っ
    0.51
     教え
    0.50
     होमवर्क
    0.49
     そして
    0.49
     ねえ
    0.49
     kosakata
    0.48
     libertarian
    0.48
     剤
    0.48
     ラック
    0.48
    Activations Density 0.000%

    No Known Activations