© 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. 106621
    Prev
    Next
    INDEX
    Explanations

    academic paper sections

    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
    ㄓ
    -0.90
     vī
    -0.88
    theil
    -0.84
    ῴ
    -0.82
    гән
    -0.82
     ARMS
    -0.81
     viață
    -0.81
     тока
    -0.80
     khawatir
    -0.80
    ㄐ
    -0.80
    POSITIVE LOGITS
     Br
    0.80
    sbin
    0.79
     exit
    0.75
    ème
    0.75
    Hiding
    0.73
     рису
    0.71
    sso
    0.70
     эмо
    0.69
    ysteine
    0.69
    <thead>
    0.69
    Activations Density 0.000%

    No Known Activations