© 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. 12313
    Prev
    Next
    INDEX
    Explanations

    a, his, that, other, us, moderate

    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
    </b>
    -1.88
     cambiando
    -1.78
    S
    -1.69
     comprando
    -1.67
     If
    -1.66
    W
    -1.63
     intensa
    -1.63
    \
    -1.61
    ꦩ
    -1.57
     foremost
    -1.51
    POSITIVE LOGITS
    ᐕ
    2.47
    咵
    2.30
    
    2.22
    
    2.14
    ⸎
    2.11
    錞
    2.11
    踅
    2.06
    
    2.05
    蹓
    2.02
    METHODOLOGY
    1.98
    Activations Density 0.048%

    No Known Activations