© 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. 189410
    Prev
    Next
    INDEX
    Explanations

    core competencies, real star, least away

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

    non-English punctuation

    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
     headed
    0.48
    цна
    0.47
    *{-
    0.45
     vetted
    0.42
     headings
    0.42
    켤
    0.42
    -*
    0.41
     Roberta
    0.41
     Beur
    0.40
     Кур
    0.40
    POSITIVE LOGITS
    เกิด
    0.50
    ੨
    0.48
    溲
    0.47
     কর্মী
    0.46
     जैसी
    0.45
    沇
    0.44
     مواقع
    0.43
    ออก
    0.43
     отношение
    0.42
     mengeluarkan
    0.42
    Activations Density 0.000%

    No Known Activations