© 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. 5422
    Prev
    Next
    INDEX
    Explanations

    key findings

    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
     চেষ্টা
    0.40
     보기
    0.40
     преду
    0.39
     ڕ
    0.39
     చేసుకోవ
    0.37
     Uses
    0.36
     Undo
    0.36
    嗤
    0.36
     использоваться
    0.36
     enveloping
    0.36
    POSITIVE LOGITS
     findings
    2.20
    findings
    1.89
    Findings
    1.85
     discovered
    1.84
     Findings
    1.84
    发现
    1.78
     discoveries
    1.77
    發現
    1.77
     발견
    1.70
     ditemukan
    1.59
    Activations Density 0.022%

    No Known Activations