© 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. 93278
    Prev
    Next
    INDEX
    Explanations

    auto prefixes

    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
    anza
    -0.82
     ema
    -0.79
    inator
    -0.79
     сім
    -0.77
    Rü
    -0.77
    Legături
    -0.75
    Ŏ
    -0.75
     должно
    -0.73
    ذ
    -0.73
     assess
    -0.72
    POSITIVE LOGITS
     auto
    1.09
     Auto
    1.02
    auto
    0.94
     AUTO
    0.91
     авто
    0.86
    Auto
    0.85
    magitan
    0.81
     queijo
    0.77
    んじゃ
    0.77
     自动
    0.76
    Activations Density 0.042%

    No Known Activations