© 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. 130489
    Prev
    Next
    INDEX
    Explanations

    EACH SCHOOL, few college

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

    prepositions, articles, or conjunctions

    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
    攫
    0.48
     ক্যান্টনমেন্ট
    0.45
     caminos
    0.45
     diverted
    0.43
    経路
    0.43
    éric
    0.43
    ாதார
    0.42
     purporting
    0.42
    衩
    0.42
    東北
    0.42
    POSITIVE LOGITS
    Text
    0.50
    SPORT
    0.49
     ITEMIZED
    0.49
    म
    0.48
    dib
    0.47
    deki
    0.47
     Text
    0.46
     disampaikan
    0.45
    trial
    0.45
    POP
    0.44
    Activations Density 0.000%

    No Known Activations