© 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. 186905
    Prev
    Next
    INDEX
    Explanations

    No fee, No commissions, No repair costs

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

    abstract concepts

    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
     mocker
    0.48
    驿
    0.46
    副
    0.46
    াইলেন
    0.45
    捜
    0.45
     লক্ষ
    0.45
    เก
    0.44
    国
    0.44
    楽器
    0.44
    何か
    0.44
    POSITIVE LOGITS
    7
    0.52
     Grac
    0.51
    ity
    0.50
    cannot
    0.50
    click
    0.49
    unately
    0.48
     Regen
    0.48
    ic
    0.48
     Genova
    0.48
    Approach
    0.47
    Activations Density 0.001%

    No Known Activations