© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60133
    Prev
    Next
    INDEX
    Explanations

    java collections and imports

    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
     борьбе
    -1.56
    <>
    -1.48
    ',
    -1.36
    ių
    -1.30
     =
    -1.24
    ictwa
    -1.24
     indien
    -1.23
    lerin
    -1.22
    了一会儿
    -1.21
     soldat
    -1.20
    POSITIVE LOGITS
     it
    1.91
     how
    1.76
    They
    1.72
     they
    1.71
     them
    1.56
     these
    1.51
    他們
    1.48
     Họ
    1.46
     what
    1.46
     traducciones
    1.43
    Activations Density 0.006%

    No Known Activations