© 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. 78121
    Prev
    Next
    INDEX
    Explanations

    This week on, Anne Bannerman

    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
    cuisine
    -0.84
    付けて
    -0.83
     inhibitors
    -0.79
     September
    -0.79
     ObjectMapper
    -0.75
     both
    -0.75
     kesulitan
    -0.75
     جلوگیری
    -0.75
    ？）
    -0.75
     مختلف
    -0.75
    POSITIVE LOGITS
     supuestamente
    0.93
     approxim
    0.92
    insic
    0.90
     aparentemente
    0.88
    男生
    0.88
    mittelt
    0.87
     amazingly
    0.85
     Nauk
    0.85
     inflam
    0.84
     evocative
    0.83
    Activations Density 0.000%

    No Known Activations