© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 188062
    Prev
    Next
    INDEX
    Explanations

    events and experiences

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

    parts of projects or frameworks

    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
    ل
    0.54
    Diese
    0.54
    pot
    0.53
    פל
    0.52
    ze
    0.51
    ur
    0.50
    TRI
    0.50
    ش
    0.50
    ber
    0.50
    وارد
    0.50
    POSITIVE LOGITS
     Colegio
    0.50
    ClInclude
    0.50
     CRS
    0.49
    лардан
    0.49
     Blazer
    0.46
     coverings
    0.45
     faults
    0.44
     товари
    0.44
     malignancies
    0.44
     Mér
    0.43
    Activations Density 0.000%

    No Known Activations