© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108977
    Prev
    Next
    INDEX
    Explanations

    PHP code execution

    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
    ’，
    -1.05
     obviously
    -1.04
     intended
    -1.02
     forças
    -1.02
     polícia
    -0.98
     Figure
    -0.96
    到的
    -0.95
     come
    -0.94
    ers
    -0.94
     anche
    -0.93
    POSITIVE LOGITS
     بشأن
    0.97
    ('');
    0.95
     TAI
    0.93
     unieke
    0.93
    ちな
    0.91
    职工
    0.90
     ingeniero
    0.89
    ";
    0.89
     spraw
    0.88
    jspx
    0.88
    Activations Density 0.004%

    No Known Activations