© 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. 147917
    Prev
    Next
    INDEX
    Explanations

    email client, crochet hook

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

    punctuation and special characters

    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
    ওয়ার
    0.48
     Kaspersky
    0.46
     Gilles
    0.44
     Helms
    0.44
     Sche
    0.44
     KPMG
    0.43
     কঠ
    0.43
    ᄀ
    0.42
     faute
    0.42
     UNIX
    0.41
    POSITIVE LOGITS
     ভারতে
    0.50
    印度
    0.49
    regardless
    0.48
    鄉
    0.46
    體
    0.46
    Indians
    0.46
    yre
    0.44
    autumn
    0.44
    odiac
    0.44
    澳洲
    0.43
    Activations Density 0.000%

    No Known Activations