© 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. 1002
    Prev
    Next
    INDEX
    Explanations

    adsorption/equipment related descriptions

    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
    نجليزية
    0.30
    нкү
    0.30
    恈
    0.30
    Ин
    0.29
    ل
    0.29
    艐
    0.28
    垪
    0.28
    䘚
    0.28
    被称为
    0.28
    বঙ্গ
    0.27
    POSITIVE LOGITS
     각종
    0.33
     adsor
    0.33
     equipments
    0.33
     adsorption
    0.31
     signboard
    0.30
     interlayer
    0.30
     oneself
    0.30
     、
    0.30
     auster
    0.30
     elastomer
    0.30
    Activations Density 0.003%

    No Known Activations