© 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. 25901
    Prev
    Next
    INDEX
    Explanations

    string lights

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

    depends on circumstances

    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
    د
    0.43
     asupra
    0.43
     inconsistencies
    0.43
    <start_of_image>
    0.43
     naira
    0.42
     стоимости
    0.42
     maritime
    0.41
     நம்ப
    0.41
    ج
    0.41
     unto
    0.41
    POSITIVE LOGITS
     環境
    0.48
    🖌
    0.46
    Wm
    0.46
     环境
    0.46
     Autoren
    0.45
     作者
    0.45
    ድግዳ
    0.45
    edRight
    0.45
    栍
    0.45
    winkel
    0.45
    Activations Density 0.000%

    No Known Activations