© 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-262K
    7. 41273
    Prev
    Next
    INDEX
    Explanations

    local restaurants, regulates enzymes

    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_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
    繍
    0.48
     payloads
    0.45
    飼
    0.45
     adsorb
    0.44
     comunicarse
    0.43
    ЗА
    0.43
    ใน
    0.43
     КА
    0.42
     dimerization
    0.42
     Inheritance
    0.42
    POSITIVE LOGITS
    èrement
    0.51
     Straßen
    0.49
    zetek
    0.49
    棤
    0.48
    ners
    0.48
     réf
    0.47
     royaume
    0.47
    direccion
    0.47
     මෙම
    0.47
    kette
    0.46
    Activations Density 0.001%

    No Known Activations