© 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-65K
    7. 20127
    Prev
    Next
    INDEX
    Explanations

    bolding and emphasis

    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_65k_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
     $$
    0.44
    1
    0.42
    enti
    0.42
    æ
    0.41
    elleen
    0.40
     G
    0.39
    7
    0.39
     be
    0.39
     Đ
    0.39
    ru
    0.38
    POSITIVE LOGITS
     môn
    0.43
    Musik
    0.39
    लक्ष्मी
    0.38
    бло
    0.36
     więc
    0.36
    Defs
    0.36
    ্টের
    0.36
    然而
    0.35
    目を
    0.35
    ាញ់
    0.35
    Activations Density 0.048%

    No Known Activations