© 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. 178481
    Prev
    Next
    INDEX
    Explanations

    historical jobs

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

    Fumio Kishida explained

    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
    Tổng
    0.55
    Фі
    0.55
    𝗡
    0.54
     Faktoren
    0.53
    𝗩
    0.52
    壞
    0.51
     бясплатна
    0.51
    漃
    0.50
    éditeur
    0.50
    RAND
    0.50
    POSITIVE LOGITS
     rhetoric
    0.50
     by
    0.48
     pump
    0.46
     ry
    0.46
    pump
    0.45
    obs
    0.44
     thickness
    0.43
     delinquency
    0.43
    egan
    0.43
     for
    0.42
    Activations Density 0.000%

    No Known Activations