© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 84346
    Prev
    Next
    INDEX
    Explanations

    descriptions of people and presentations

    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
     নামে
    0.41
     이름
    0.38
    ूव
    0.36
    出门
    0.36
    歓
    0.35
    陰
    0.35
     bath
    0.35
    롬
    0.35
    liery
    0.34
     idiots
    0.34
    POSITIVE LOGITS
     Nikola
    0.40
    ionalità
    0.40
     Wikiped
    0.39
    ニー
    0.39
    startswith
    0.38
    pip
    0.37
    ocultural
    0.37
    ✺
    0.37
    装備
    0.37
    minimize
    0.37
    Activations Density 0.000%

    No Known Activations