© 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. 72429
    Prev
    Next
    INDEX
    Explanations

    Mono prefix

    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
     it
    -3.06
     However
    -2.92
     verbess
    -2.91
    注意事
    -2.91
     แต่
    -2.88
     They
    -2.88
    衎
    -2.77
     If
    -2.75
    炻
    -2.72
     The
    -2.67
    POSITIVE LOGITS
    鉭
    3.11
    깐
    2.59
    骉
    2.53
    ⚋
    2.48
    ༔
    2.48
    ～　
    2.47
    ・・・・・
    2.47
    呖
    2.45
    　　-
    2.44
    꿉
    2.42
    Activations Density 0.007%

    No Known Activations