© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 35570
    Prev
    Next
    INDEX
    Explanations

    Active Level Password

    np_acts-logits-general · gemini-2.5-flash-lite

    background-color values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ز
    1.13
    ب
    1.10
    ي
    0.96
    م
    0.94
    ти
    0.91
    该
    0.89
    美国
    0.85
    ल
    0.83
    ปี
    0.81
    ۰
    0.81
    POSITIVE LOGITS
    ьте
    1.05
    BackgroundColor
    0.88
    Nome
    0.86
    Password
    0.79
    getVisibility
    0.75
    のない
    0.75
    Location
    0.73
    CurrentImageData
    0.73
    Active
    0.72
    Level
    0.71
    Activations Density 0.108%

    No Known Activations