© 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. 93037
    Prev
    Next
    INDEX
    Explanations

    urls, external links, and media references

    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
    owano
    -0.85
     segi
    -0.85
    shadowRadius
    -0.84
     wasn
    -0.82
    XICO
    -0.81
    chauen
    -0.78
    WIFI
    -0.77
     Segal
    -0.77
     Xue
    -0.76
     whereas
    -0.76
    POSITIVE LOGITS
    вій
    0.81
     http
    0.78
     създа
    0.77
    uksia
    0.73
     if
    0.73
    ristiano
    0.72
     Demos
    0.71
     pname
    0.71
    phim
    0.71
     queryParams
    0.71
    Activations Density 0.022%

    No Known Activations