© 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. 111504
    Prev
    Next
    INDEX
    Explanations

    multiple fully copies

    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
     Dickinson
    0.42
     অ্যা
    0.41
     معنا
    0.41
    看向
    0.41
    媺
    0.41
     빅뱅
    0.40
    IKO
    0.40
    परे
    0.39
     वॉ
    0.39
     लॉ
    0.39
    POSITIVE LOGITS
    coupled
    0.48
    ľov
    0.45
    brought
    0.45
     popolazione
    0.44
    鸞
    0.44
     ihre
    0.44
    continuous
    0.44
    ي
    0.44
     وە
    0.43
     abras
    0.43
    Activations Density 0.009%

    No Known Activations