© 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. 30333
    Prev
    Next
    INDEX
    Explanations

    included explanations, visuals, considerations

    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
    纽约
    0.55
    意大利
    0.52
     ଏ
    0.52
    ニューヨーク
    0.52
    Selling
    0.50
    Giovanni
    0.48
     tribunals
    0.47
    Sandbox
    0.47
     دی
    0.47
    Termination
    0.47
    POSITIVE LOGITS
     (*
    0.47
     Parser
    0.47
     C
    0.46
     descriptor
    0.44
     (++
    0.42
     M
    0.41
     (+)
    0.41
     T
    0.40
     Th
    0.40
     Suppose
    0.40
    Activations Density 0.001%

    No Known Activations