© 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. 183263
    Prev
    Next
    INDEX
    Explanations

    drug busts

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

    Brandenburg Gate

    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
    notifier
    0.52
    вить
    0.47
    प्र
    0.45
    ಲ್ಯ
    0.44
    낚
    0.43
    signer
    0.43
    Eth
    0.43
    тяги
    0.41
    prz
    0.41
    ಡ
    0.40
    POSITIVE LOGITS
     usuários
    0.47
     č
    0.46
     sond
    0.46
     vasos
    0.45
    ič
    0.45
     seu
    0.44
    噌
    0.44
     SSP
    0.44
     refinements
    0.43
     kamera
    0.43
    Activations Density 0.000%

    No Known Activations