© 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. 40-GEMMASCOPE-2-RES-262K
    7. 4520
    Prev
    Next
    INDEX
    Explanations

    sh sound and common prefixes

    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_40_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
     შემდეგ
    0.42
    संख्यक
    0.41
    愘
    0.39
    苏
    0.39
    ttet
    0.38
    くらいの
    0.38
    ейчас
    0.38
    <unused0>
    0.38
    后续
    0.38
     initialization
    0.37
    POSITIVE LOGITS
    Sh
    0.83
     Sh
    0.77
     SH
    0.77
     sh
    0.75
     ஷ
    0.66
     シャ
    0.66
     Ш
    0.64
     श
    0.63
     ష
    0.62
     শ
    0.59
    Activations Density 0.066%

    No Known Activations