© 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. 93303
    Prev
    Next
    INDEX
    Explanations

    programming data structures and code

    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
     (
    -0.99
     even
    -0.88
    }(
    -0.87
     first
    -0.85
    ！(
    -0.84
     so
    -0.76
      (
    -0.75
     $(
    -0.74
    。　　
    -0.74
     specific
    -0.73
    POSITIVE LOGITS
     [
    2.86
    [
    2.47
    ['
    2.38
    ["
    2.22
    [$
    2.08
    [(
    2.06
     ['
    2.05
     ["
    2.00
    [\
    1.95
     [(
    1.66
    Activations Density 0.162%

    No Known Activations