© 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. 217951
    Prev
    Next
    INDEX
    Explanations

    recording actions and states

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

    tricky pricing

    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
     двох
    0.49
    šit
    0.48
    ढ़ाई
    0.47
    vline
    0.46
    дзі
    0.44
    
    0.44
    ｾ
    0.44
     своїх
    0.44
    に対応
    0.44
    齬
    0.44
    POSITIVE LOGITS
     exot
    0.48
     Raul
    0.47
     T
    0.45
     DIA
    0.44
     location
    0.44
     sediment
    0.43
     C
    0.43
     Baron
    0.43
     tqdm
    0.42
     Hé
    0.42
    Activations Density 0.003%

    No Known Activations