© 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. 178378
    Prev
    Next
    INDEX
    Explanations

    offers products

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

    angle of attack

    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
     for
    0.58
    ham
    0.51
    s
    0.51
     revisions
    0.50
    for
    0.50
     Indexes
    0.48
    ona
    0.48
    anas
    0.48
     indexes
    0.48
     IDs
    0.47
    POSITIVE LOGITS
    ﺘ
    0.49
     permitirá
    0.49
     نک
    0.48
     ಅವಕಾಶ
    0.48
    وک
    0.47
    ECON
    0.47
     जाणून
    0.47
    🛂
    0.47
    ELEASE
    0.46
     መንገድ
    0.46
    Activations Density 0.001%

    No Known Activations