© 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. 135099
    Prev
    Next
    INDEX
    Explanations

    hired coverage discordant global capturing captions depends

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

    stronger verbs

    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
     एक्सपे
    0.51
     Attitudes
    0.50
    鈈
    0.46
    佶
    0.45
    ούς
    0.45
    告
    0.44
    ohnt
    0.44
    ленное
    0.44
    hubung
    0.43
    婄
    0.43
    POSITIVE LOGITS
    to
    0.55
    as
    0.53
     Meek
    0.52
    at
    0.50
     placer
    0.50
     смотрите
    0.50
     centering
    0.50
    u
    0.50
     corral
    0.49
     parametr
    0.48
    Activations Density 0.000%

    No Known Activations