© 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. 10-GEMMASCOPE-RES-131K
    7. 71367
    Prev
    Next
    INDEX
    Explanations

    nice

    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
    ㉕
    -2.03
     to
    -1.91
    Odpovědět
    -1.85
    镠
    -1.82
     verschied
    -1.82
     製品
    -1.73
    噥
    -1.70
    鉿
    -1.63
    งิน
    -1.61
    嫱
    -1.61
    POSITIVE LOGITS
    。"
    1.70
    ग़
    1.50
     consegu
    1.41
     мной
    1.40
     idea
    1.39
     lik
    1.37
    
    1.37
     and
    1.37
    ("
    1.34
     valida
    1.31
    Activations Density 0.003%

    No Known Activations