© 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. 170625
    Prev
    Next
    INDEX
    Explanations

    Talmud uses, garage door, secret German

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

    question format

    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
    و
    0.53
     zako
    0.52
     registra
    0.48
    ورا
    0.45
     terminer
    0.43
    وست
    0.42
     butchers
    0.42
     wissenschaft
    0.42
    sistema
    0.42
     geni
    0.42
    POSITIVE LOGITS
    າຍ
    0.49
    藤
    0.44
    পুরের
    0.42
    ках
    0.42
    icycle
    0.42
    કાશ
    0.42
    acă
    0.41
    khane
    0.41
    Size
    0.41
    umping
    0.40
    Activations Density 0.000%

    No Known Activations