© 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. 93202
    Prev
    Next
    INDEX
    Explanations

    Qiannan Buyei and Miao Autonomous Prefecture

    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
    мя
    -0.79
    لعاب
    -0.73
    ateri
    -0.72
     egenskaper
    -0.70
     sympathize
    -0.69
    }">
    -0.68
     sympathetic
    -0.67
    Pak
    -0.67
    czy
    -0.67
    看護
    -0.66
    POSITIVE LOGITS
    нъ
    0.77
    KHR
    0.73
     ám
    0.73
     repri
    0.71
     bará
    0.71
    Introductory
    0.69
     whit
    0.68
    Kjelder
    0.68
     shaders
    0.68
    heder
    0.67
    Activations Density 0.015%

    No Known Activations