© 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. 57864
    Prev
    Next
    INDEX
    Explanations

    Voy, Voyk, Vojvodina, Voynichian

    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
     Phosphorus
    -0.77
     〈
    -0.75
    ’?
    -0.75
    ubon
    -0.75
     pronom
    -0.75
    '!
    -0.73
     chế
    -0.73
    田村
    -0.72
    责任
    -0.71
     pater
    -0.70
    POSITIVE LOGITS
    
    0.73
     wars
    0.70
    tek
    0.70
    نية
    0.68
     peito
    0.67
    パチ
    0.67
    jmniej
    0.65
    CSD
    0.65
     cocina
    0.65
     mö
    0.65
    Activations Density 0.036%

    No Known Activations