© 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. 10-GEMMASCOPE-RES-131K
    7. 84359
    Prev
    Next
    INDEX
    Explanations

    political leaders dictators

    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_10/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
     '
    -1.84
     triliun
    -1.66
    。“
    -1.61
    vanju
    -1.61
     antworte
    -1.58
    .'
    -1.57
    水墨
    -1.56
     applaud
    -1.56
    ,"
    -1.55
     gewähr
    -1.52
    POSITIVE LOGITS
    欒
    1.68
    用
    1.67
     gratuita
    1.63
    龶
    1.50
    ↵
    1.45
    is
    1.44
     raconte
    1.38
     you
    1.34
     ilumina
    1.33
    ति
    1.31
    Activations Density 0.016%

    No Known Activations