© 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. 200377
    Prev
    Next
    INDEX
    Explanations

    acrylic, acrylamide, acrylonitrile

    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
     Lombok
    0.42
     ScriptInterface
    0.42
    ebu
    0.39
    GO
    0.39
    yas
    0.39
     tộc
    0.37
     Ç
    0.37
    Ç
    0.36
    recur
    0.36
    owany
    0.36
    POSITIVE LOGITS
     acrylic
    0.50
    Acrylic
    0.46
     acry
    0.46
    гона
    0.45
     Acrylic
    0.44
     ACR
    0.41
     Milky
    0.41
    acrylic
    0.39
     encaps
    0.38
     чуть
    0.38
    Activations Density 0.021%

    No Known Activations