© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10807
    Prev
    Next
    INDEX
    Explanations

    place names following punctuation

    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_31_width_16k_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
     или
    0.44
     special
    0.43
     speci
    0.43
    c
    0.43
    tencent
    0.42
    மானு
    0.42
    SPECIAL
    0.42
     degeneracy
    0.42
     приве
    0.42
    m
    0.42
    POSITIVE LOGITS
    atering
    0.44
    🤵
    0.39
    adoop
    0.39
    た
    0.38
    实现的
    0.38
    族的
    0.38
     कश्मीर
    0.37
    のは
    0.37
    estimators
    0.37
     ച
    0.37
    Activations Density 0.085%

    No Known Activations