© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 53920
    Prev
    Next
    INDEX
    Explanations

    mathematical libraries

    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
    调试
    -0.71
    的新
    -0.70
    piper
    -0.68
     игроков
    -0.68
     יְ
    -0.68
     Wortes
    -0.67
    uppe
    -0.66
     groaned
    -0.66
     during
    -0.65
    ose
    -0.65
    POSITIVE LOGITS
    Musi
    0.79
    StartIndex
    0.79
     blas
    0.79
     pão
    0.77
    avoit
    0.77
     poseen
    0.73
     Cognition
    0.73
    Wikis
    0.73
     computation
    0.71
    blas
    0.71
    Activations Density 0.028%

    No Known Activations