© 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. 93476
    Prev
    Next
    INDEX
    Explanations

    C++ iterators and auto declarations

    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
    lya
    -0.87
    czna
    -0.86
     diantaranya
    -0.82
     құ
    -0.76
    USING
    -0.73
    omeness
    -0.72
     USING
    -0.71
     vorhanden
    -0.71
     utilizzati
    -0.70
    ولی
    -0.70
    POSITIVE LOGITS
     it
    2.41
     [
    1.41
     It
    1.31
    It
    1.22
     &[
    1.16
     iter
    1.09
    &&
    1.06
     &&
    0.99
    Pair
    0.97
    ',[
    0.96
    Activations Density 0.008%

    No Known Activations