© 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. 99887
    Prev
    Next
    INDEX
    Explanations

    ascension and maximum

    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
    ↵↵
    -2.64
    
    -2.55
    ဴ
    -2.45
    醅
    -2.41
    Ольга
    -2.38
    用の
    -2.34
    tarif
    -2.33
    倧
    -2.33
    赑
    -2.31
    ،
    -2.28
    POSITIVE LOGITS
    or
    2.66
    犽
    2.34
    冋
    2.33
    borderFill
    2.23
     —
    2.16
    苾
    2.16
    鲼
    2.11
    '
    2.02
     sette
    1.96
    鋱
    1.95
    Activations Density 0.001%

    No Known Activations