© 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. 108569
    Prev
    Next
    INDEX
    Explanations

    technical syntax and commands

    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
    Pues
    0.51
    Let
    0.49
    є
    0.49
    Ін
    0.47
    Screw
    0.46
    대의
    0.46
    간
    0.46
     이번
    0.45
    Nas
    0.45
    Difficulty
    0.45
    POSITIVE LOGITS
     Decedent
    0.49
     more
    0.48
     harvest
    0.47
     cool
    0.46
     agribusiness
    0.46
     Coron
    0.45
     economic
    0.45
     fourteenth
    0.45
     Economic
    0.44
    سازی
    0.44
    Activations Density 0.004%

    No Known Activations