© 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. 34-GEMMASCOPE-RES-131K
    7. 31512
    Prev
    Next
    INDEX
    Explanations

    states and places

    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_34/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
    屈
    -0.77
    Ла
    -0.77
     virtuous
    -0.76
    ٢
    -0.75
    BUS
    -0.72
    লা
    -0.72
    stdafx
    -0.71
    Hãy
    -0.71
    TOC
    -0.70
     "\
    -0.69
    POSITIVE LOGITS
     Auro
    0.98
    ,–
    0.85
     CEM
    0.84
    iliares
    0.82
     Integral
    0.81
     Belgi
    0.80
     seiz
    0.79
     机器
    0.79
    thoven
    0.75
    出错
    0.74
    Activations Density 0.011%

    No Known Activations