© 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. 57926
    Prev
    Next
    INDEX
    Explanations

    jquery javascript or jquery ajax

    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
     bleak
    -0.79
     Daerah
    -0.78
    wörter
    -0.76
    Kazakhstan
    -0.76
     blom
    -0.75
    Trend
    -0.75
     naa
    -0.75
     keren
    -0.75
    hran
    -0.74
     nera
    -0.74
    POSITIVE LOGITS
    ControllerAdvice
    0.87
    ueve
    0.78
    يفة
    0.78
    (($
    0.77
    Morfologia
    0.75
     hyg
    0.73
    蚓
    0.73
     pflegen
    0.73
     сообщи
    0.73
    ilibre
    0.73
    Activations Density 0.043%

    No Known Activations