© 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. 31741
    Prev
    Next
    INDEX
    Explanations

    descriptive words after punctuation

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

    numbers and technical terms

    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
    這位
    0.55
    पु
    0.53
    这位
    0.50
    デー
    0.48
    塑料
    0.48
    鋈
    0.47
    ૄ
    0.47
    飪
    0.46
    ZIONE
    0.46
    BOOKS
    0.46
    POSITIVE LOGITS
    aug
    0.51
    env
    0.49
     bing
    0.48
    nan
    0.46
     dile
    0.46
     palms
    0.45
    enn
    0.45
     строки
    0.45
     rigs
    0.44
    yl
    0.44
    Activations Density 0.000%

    No Known Activations