© 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. 64988
    Prev
    Next
    INDEX
    Explanations

    words following punctuation

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

    long-standing customs

    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
     narrates
    0.50
     ге
    0.47
    焰
    0.45
     بعنوان
    0.44
     торже
    0.43
     тел
    0.43
     colorChoice
    0.43
    自然的
    0.42
     раді
    0.42
    🏔
    0.42
    POSITIVE LOGITS
    y
    0.55
     abu
    0.50
     Hereford
    0.48
    m
    0.47
     B
    0.47
    ky
    0.47
     pants
    0.47
     Dorset
    0.46
    gub
    0.46
    kip
    0.45
    Activations Density 0.000%

    No Known Activations