© 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. 78641
    Prev
    Next
    INDEX
    Explanations

    method calls in code

    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
    Текст
    -0.91
     even
    -0.90
    УДК
    -0.88
     lucu
    -0.88
    isLoaded
    -0.88
     berke
    -0.83
     dima
    -0.80
     berta
    -0.79
    Willkommen
    -0.79
     gigi
    -0.77
    POSITIVE LOGITS
    🕛
    0.79
     Motion
    0.78
    oty
    0.77
     motion
    0.76
     struggles
    0.75
    より
    0.75
     request
    0.73
    ndry
    0.73
    getRequest
    0.73
    Motion
    0.73
    Activations Density 0.005%

    No Known Activations