© 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. 38735
    Prev
    Next
    INDEX
    Explanations

    Python dunder methods

    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
    だが
    0.46
    Grace
    0.45
     Grace
    0.44
    Home
    0.42
     whatnot
    0.42
    {
    0.40
    气的
    0.39
     {})
    0.38
     ח
    0.38
    ड़ों
    0.38
    POSITIVE LOGITS
    ن
    0.52
    ро
    0.51
    indagi
    0.50
    ʻ
    0.50
    自己的
    0.48
    ה
    0.46
    andre
    0.46
     integrante
    0.44
    ر
    0.44
    ב
    0.44
    Activations Density 0.006%

    No Known Activations