© 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-65K
    7. 36869
    Prev
    Next
    INDEX
    Explanations

    csharp code structures

    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_65k_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
     किराया
    0.45
     noirâtre
    0.44
    ęła
    0.43
     wspom
    0.41
    újt
    0.41
    ത്ര
    0.41
     नमी
    0.41
    🧴
    0.41
    溦
    0.40
    zneim
    0.40
    POSITIVE LOGITS
    判断
    0.43
     circuits
    0.42
    Map
    0.39
    Creo
    0.39
     判断
    0.37
     calculations
    0.37
    Create
    0.36
    Authorities
    0.36
     reputation
    0.36
    Drop
    0.36
    Activations Density 0.002%

    No Known Activations