Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 25362
    Prev
    Next
    INDEX
    Explanations

    AI discourse

    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
    -}$
    0.43
     injustices
    0.42
    ذاب
    0.41
     injustice
    0.41
     supplement
    0.40
     stems
    0.40
     pren
    0.39
    ظ
    0.38
    vecb
    0.37
    ሉም
    0.37
    POSITIVE LOGITS
     используются
    0.54
     Иң
    0.54
     ប៉ុ
    0.51
     แต่
    0.51
     μέχρι
    0.49
     название
    0.49
    ﺍ
    0.48
     صہیونی
    0.47
     轻
    0.47
     혹은
    0.46
    Activations Density 0.004%

    No Known Activations