© 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. 57085
    Prev
    Next
    INDEX
    Explanations

    purpose or direction

    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
    ﺶ
    -0.86
     poc
    -0.85
     parrots
    -0.82
     commandment
    -0.82
    
    -0.82
     日常
    -0.81
     overwhelmingly
    -0.80
     convoluted
    -0.79
    Наталья
    -0.79
    Mika
    -0.79
    POSITIVE LOGITS
     Aim
    1.33
    Aim
    1.23
     aim
    1.21
    aim
    1.07
     squarely
    0.96
     AIM
    0.96
    🎯
    0.94
    ком
    0.92
    lessly
    0.91
    higher
    0.87
    Activations Density 0.027%

    No Known Activations