© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 8393
    Prev
    Next
    INDEX
    Explanations

    colors and text formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    텃
    0.42
    >:</
    0.38
    ="*"
    0.38
    パン
    0.36
    嫁
    0.35
    ༠
    0.35
     tac
    0.34
    pecia
    0.34
     sprou
    0.33
     নদীর
    0.33
    POSITIVE LOGITS
     Sorry
    0.39
     Tops
    0.38
     closes
    0.38
     No
    0.38
     cerr
    0.38
    TextColor
    0.38
     Commence
    0.37
     Foreground
    0.37
     Colours
    0.36
    子
    0.35
    Activations Density 0.000%

    No Known Activations