© 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. 191077
    Prev
    Next
    INDEX
    Explanations

    relevant medications

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

    discovering files transactions

    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
    سک
    0.50
     foresight
    0.44
     demarcation
    0.44
    odem
    0.44
     fenced
    0.43
    在哪
    0.42
    መሳ
    0.42
    채
    0.42
     scept
    0.41
     recounted
    0.41
    POSITIVE LOGITS
    parks
    0.52
    rå
    0.52
    hôtel
    0.52
    ifício
    0.51
     Shakti
    0.50
    m
    0.49
     hôtels
    0.48
     информацией
    0.48
     liye
    0.48
    мок
    0.48
    Activations Density 0.000%

    No Known Activations