© 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. 226856
    Prev
    Next
    INDEX
    Explanations

    named insured Jesus Christ

    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
     chiefly
    0.47
    ffi
    0.46
     NSFW
    0.45
    ικοί
    0.45
    <0xBB>
    0.44
    ᓄ
    0.44
    重視
    0.43
     worrisome
    0.42
     canaux
    0.42
    嘢
    0.42
    POSITIVE LOGITS
    িদ্ধ
    0.47
     কাটিয়ে
    0.44
    boats
    0.42
     विधानसभा
    0.41
    일
    0.41
    Util
    0.41
    collegiate
    0.40
    利用
    0.40
    Applicants
    0.40
    Viewer
    0.40
    Activations Density 0.000%

    No Known Activations