© 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. 39423
    Prev
    Next
    INDEX
    Explanations

    hair, loss, styles, knot

    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
    缡
    -2.67
    ：《
    -2.64
     faune
    -2.63
    d
    -2.55
    E
    -2.44
     δεν
    -2.42
    品的
    -2.42
    慥
    -2.38
    镲
    -2.38
     —
    -2.33
    POSITIVE LOGITS
    
    3.06
     we
    2.72
     cambian
    2.42
    ра
    2.41
    其他
    2.38
     foremost
    2.33
     zwanzig
    2.28
    㐂
    2.28
     definitive
    2.27
     subtleties
    2.27
    Activations Density 0.007%

    No Known Activations