© 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. 56149
    Prev
    Next
    INDEX
    Explanations

    Dwarf Planets, Blade Servers, logout

    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
    Not in Any Lists

    No Comments

    Negative Logits
    checker
    0.46
    Cleaning
    0.45
    ルメ
    0.44
    serviceTime
    0.44
    Melitaea
    0.44
    Healing
    0.44
    Hydrochloride
    0.44
    ㄉ
    0.44
    婦
    0.43
    Emergency
    0.43
    POSITIVE LOGITS
     blogs
    0.52
     tangible
    0.51
     porque
    0.49
     karena
    0.48
     hidup
    0.47
     जिनके
    0.47
     pricey
    0.47
     vì
    0.46
     தங்கள்
    0.46
     their
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.