© 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. 34-GEMMASCOPE-RES-131K
    7. 31809
    Prev
    Next
    INDEX
    Explanations

    code style descriptions

    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
     đậu
    -0.78
     달
    -0.77
    肄
    -0.71
    Zor
    -0.70
     tốc
    -0.70
    気がする
    -0.69
     نهاية
    -0.69
    珉
    -0.69
     ビジネス
    -0.69
     localizar
    -0.68
    POSITIVE LOGITS
     STYLE
    0.96
     Cip
    0.85
    textStyle
    0.81
    sede
    0.79
    Side
    0.76
     Guild
    0.75
    gog
    0.75
    lampu
    0.73
     Side
    0.73
    style
    0.73
    Activations Density 0.001%

    No Known Activations