© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12787
    Prev
    Next
    INDEX
    Explanations

    one who

    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_262k_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
     Ш
    0.47
     जैसी
    0.43
     programmable
    0.43
    hile
    0.43
     своей
    0.42
     itself
    0.42
    ую
    0.42
    hpp
    0.41
    作为一个
    0.40
    υ
    0.40
    POSITIVE LOGITS
    率先
    0.63
     recipients
    0.59
     recipient
    0.59
     initiate
    0.56
    先に
    0.55
    最初に
    0.54
     beneficiary
    0.53
     beneficiaries
    0.52
     instigated
    0.51
     benefited
    0.50
    Activations Density 0.047%

    No Known Activations