© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99938
    Prev
    Next
    INDEX
    Explanations

    distributed under the License

    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
    ksikon
    -0.79
     tse
    -0.71
     Medan
    -0.71
    tess
    -0.70
     tuan
    -0.68
     tė
    -0.68
    Full
    -0.68
     Collin
    -0.67
     karo
    -0.66
     full
    -0.66
    POSITIVE LOGITS
    ThroughAttribute
    0.72
     معرف
    0.70
     bajas
    0.69
    Heights
    0.68
     Method
    0.68
    onnay
    0.67
    ensioni
    0.67
    uluş
    0.67
     populace
    0.66
     pal
    0.66
    Activations Density 0.087%

    No Known Activations