© 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. 135020
    Prev
    Next
    INDEX
    Explanations

    story.Pass the.not personally.oppressive to.subject

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

    neurons

    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
    कार
    0.56
    कर्ता
    0.47
    贖
    0.46
     sums
    0.45
    տն
    0.45
     commuting
    0.45
    ﻓ
    0.44
    ПР
    0.43
    嘯
    0.43
    麃
    0.43
    POSITIVE LOGITS
    ;
    0.52
    rya
    0.48
    fadeIn
    0.48
     =
    0.48
    len
    0.47
    ittää
    0.46
    anilide
    0.46
    GaussianBlur
    0.45
    round
    0.45
    adrenergic
    0.45
    Activations Density 0.002%

    No Known Activations