© 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. 210818
    Prev
    Next
    INDEX
    Explanations

    safety standards

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

    Gothic Quarter

    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
     көр
    0.45
     réalise
    0.45
    ऊदी
    0.44
    畬
    0.44
     हुईं
    0.43
    어져
    0.43
    鏻
    0.43
    鈁
    0.43
    usso
    0.43
    进行的
    0.43
    POSITIVE LOGITS
    field
    0.46
    drunk
    0.46
    slant
    0.45
    heaven
    0.44
     Тихо
    0.44
    bre
    0.44
    blur
    0.43
    big
    0.43
    บาง
    0.43
    sliding
    0.43
    Activations Density 0.000%

    No Known Activations