© 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. 22-GEMMASCOPE-RES-131K
    7. 397
    Prev
    Next
    INDEX
    Explanations

    level shifting

    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_22/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
    ↵
    -2.67
    面對
    -2.20
    價格
    -2.19
    ޢ
    -2.17
    
    -2.16
     voitures
    -2.06
    
    -2.06
    鸯
    -2.02
     Brings
    -1.98
    ↵↵
    -1.93
    POSITIVE LOGITS
    ଝ
    2.83
    </sup>
    2.75
    ?"
    2.64
    .'
    2.63
    ؟
    2.61
    ႐
    2.50
    )
    2.48
    ⬯
    2.47
    ྄
    2.45
     её
    2.41
    Activations Density 0.041%

    No Known Activations