© 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. 63640
    Prev
    Next
    INDEX
    Explanations

    competition results and rankings

    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
     Hiking
    -0.87
    lussen
    -0.86
     metais
    -0.82
     Tuchel
    -0.82
    caron
    -0.81
    fortawesome
    -0.80
    źni
    -0.80
     poivre
    -0.79
     racc
    -0.79
    مار
    -0.79
    POSITIVE LOGITS
    剩下的
    0.95
    merry
    0.85
     others
    0.82
     מקום
    0.77
    ных
    0.77
    Others
    0.76
     resten
    0.75
     بعدی
    0.74
    学習
    0.73
     rest
    0.72
    Activations Density 0.003%

    No Known Activations