© 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. 120162
    Prev
    Next
    INDEX
    Explanations

    taking Scale

    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
    naden
    0.38
    ">${
    0.38
     непосредственно
    0.37
    ="${
    0.37
    volle
    0.36
    mmHg
    0.36
    стоя
    0.35
    真正
    0.34
    REFLECTION
    0.34
    hive
    0.34
    POSITIVE LOGITS
     ಸಾಮಾನ್ಯ
    0.43
     виправивши
    0.37
    дьми
    0.37
     राजांनी
    0.37
    𒇷
    0.37
    迺
    0.36
    پر
    0.36
     stomach
    0.36
     creme
    0.36
     იგი
    0.36
    Activations Density 0.004%

    No Known Activations