© 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. 112903
    Prev
    Next
    INDEX
    Explanations

    numbers and Japanese/Chinese characters

    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
    0
    -3.92
    m
    -3.89
    6
    -3.38
    u
    -3.19
    ↵
    -3.17
    3
    -3.06
    4
    -3.05
    Not
    -3.05
    5
    -2.95
    2
    -2.86
    POSITIVE LOGITS
    苤
    2.95
    
    2.88
    ⃑
    2.88
    籥
    2.86
     considerado
    2.86
    犼
    2.70
     milhares
    2.63
    拇
    2.61
     révélé
    2.61
     Geografía
    2.61
    Activations Density 0.006%

    No Known Activations