© 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. 4320
    Prev
    Next
    INDEX
    Explanations

    colon-separated values or code blocks

    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
    桠
    0.54
    墀
    0.52
    耱
    0.51
    糈
    0.49
    郯
    0.48
     besoin
    0.47
    雩
    0.47
     গিয়াছেন
    0.46
    兕
    0.46
    屣
    0.46
    POSITIVE LOGITS
     default
    0.54
    ":
    0.50
     distorted
    0.50
     lexic
    0.49
    java
    0.49
    expected
    0.48
     expected
    0.47
     bizarre
    0.47
     results
    0.46
     nearly
    0.46
    Activations Density 0.278%

    No Known Activations