© 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. 78213
    Prev
    Next
    INDEX
    Explanations

    API, parameters, or tuples

    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
    ランダ
    -0.78
    burne
    -0.72
    学期
    -0.71
    centering
    -0.69
    escola
    -0.67
    撈
    -0.67
     centering
    -0.67
    瘁
    -0.67
     Clustering
    -0.66
    числе
    -0.64
    POSITIVE LOGITS
     螺
    0.68
    pointments
    0.66
     ECO
    0.63
     số
    0.63
    āj
    0.62
    Popis
    0.62
     compost
    0.62
    пью
    0.62
     Zwe
    0.62
     chô
    0.61
    Activations Density 0.045%

    No Known Activations