© 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. 31478
    Prev
    Next
    INDEX
    Explanations

    copyrighted images or content

    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
     ביום
    -0.76
     grandchild
    -0.71
     iCloud
    -0.70
    からは
    -0.69
     Aki
    -0.68
    要求
    -0.65
    alow
    -0.65
     BCG
    -0.65
    Instructions
    -0.64
    ག་
    -0.63
    POSITIVE LOGITS
     scattering
    0.79
     हुआ
    0.75
    ficulty
    0.73
    scattering
    0.72
     премии
    0.71
    ógio
    0.68
    BorderColor
    0.67
    ઠ
    0.67
     Zane
    0.67
    мяг
    0.66
    Activations Density 0.061%

    No Known Activations