© 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. 200338
    Prev
    Next
    INDEX
    Explanations

    describes actions or states

    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
     When
    0.48
     Samurai
    0.47
    clientsdetails
    0.46
     Since
    0.44
    狀
    0.43
     ROI
    0.42
     samurai
    0.42
    oya
    0.41
    rova
    0.41
    状
    0.41
    POSITIVE LOGITS
     vaginalis
    0.47
    法の
    0.46
     curators
    0.46
    नाइटेड
    0.45
    У
    0.44
     inactivated
    0.44
     curated
    0.43
     exemples
    0.43
     homogenized
    0.43
    创新
    0.42
    Activations Density 0.001%

    No Known Activations