© 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. 63881
    Prev
    Next
    INDEX
    Explanations

    origin and growth

    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
     in
    -0.82
    癸
    -0.73
    ajaan
    -0.69
    pug
    -0.68
     области
    -0.68
     by
    -0.68
    (({
    -0.66
     Haupts
    -0.66
     बताया
    -0.66
     produkcji
    -0.65
    POSITIVE LOGITS
     grew
    3.56
     evolved
    2.81
     arose
    2.78
     sprang
    2.61
     sprung
    2.59
     emerged
    2.47
     stemmed
    2.36
    grew
    2.16
     grows
    2.13
     grow
    2.09
    Activations Density 0.151%

    No Known Activations