© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 140079
    Prev
    Next
    INDEX
    Explanations

    drives with, new owner, set of

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

    current CEO

    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
    Negative Logits
    <0x0D>
    0.67
    ik
    0.51
     drew
    0.50
     Cardoso
    0.50
    _\
    0.48
     मेरा
    0.47
    ↵↵
    0.47
     doomed
    0.47
    </strong>
    0.46
    って
    0.46
    POSITIVE LOGITS
    ᷄
    0.48
    皮膚
    0.48
    สห
    0.48
    莼
    0.47
    美国的
    0.47
    ไน
    0.45
    黴
    0.44
    化的
    0.43
    蹦
    0.43
    美的
    0.42
    Activations Density 0.000%

    No Known Activations