© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104014
    Prev
    Next
    INDEX
    Explanations

    action and behaviors

    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
     作り方
    -1.82
    idade
    -1.70
    潆
    -1.69
     dorp
    -1.65
    觏
    -1.63
    tafel
    -1.63
     jeg
    -1.57
    𐍆
    -1.57
    ’
    -1.57
    </strong>
    -1.56
    POSITIVE LOGITS
     convierte
    1.95
     It
    1.93
     acciones
    1.70
     Also
    1.70
     encontrados
    1.67
    を起こ
    1.63
     neutralize
    1.63
    浑身
    1.62
     stirs
    1.61
     spasms
    1.60
    Activations Density 0.038%

    No Known Activations