© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78488
    Prev
    Next
    INDEX
    Explanations

    database queries, string formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     `${
    -1.35
    (`${
    -1.27
    `${
    -1.24
    ("[
    -1.16
    ($"{
    -1.09
    ("<
    -0.99
    ("%
    -0.90
     `<
    -0.90
    '<
    -0.90
    "[
    -0.88
    POSITIVE LOGITS
    ($"
    1.16
     $"
    0.99
     „
    0.83
     "
    0.81
    $"
    0.81
    zimy
    0.79
     deodorant
    0.77
    ={"
    0.77
     konserv
    0.75
    =>"
    0.73
    Activations Density 0.043%

    No Known Activations