© 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. 913
    Prev
    Next
    INDEX
    Explanations

    descriptive shape and feature words

    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
     Unterrichts
    -0.85
    SEB
    -0.84
     násled
    -0.84
    liai
    -0.83
    ^(@)
    -0.78
     занятий
    -0.77
    mpang
    -0.77
    ुक
    -0.77
    lysses
    -0.75
     młody
    -0.75
    POSITIVE LOGITS
    Blade
    0.81
     blade
    0.81
     lancé
    0.79
    
    0.78
    blade
    0.77
     folded
    0.77
     Blade
    0.77
    内
    0.76
    退
    0.73
    tomia
    0.72
    Activations Density 0.011%

    No Known Activations