© 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. 183280
    Prev
    Next
    INDEX
    Explanations

    ensure your offer

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

    However, but, if

    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
    Goed
    0.49
    Poll
    0.47
    든
    0.46
    선
    0.46
    साम
    0.46
     ascribe
    0.45
    Bharat
    0.45
    Ethiop
    0.44
    טל
    0.44
    똥
    0.44
    POSITIVE LOGITS
     inducted
    0.46
    endTime
    0.44
     BNP
    0.44
     खुलासा
    0.44
    ご注意
    0.43
     unplanned
    0.43
     প্রকাশ
    0.43
     ユ
    0.42
     incubated
    0.42
    同時
    0.42
    Activations Density 0.006%

    No Known Activations