© 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. 138918
    Prev
    Next
    INDEX
    Explanations

    explains how things are structured

    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
    ri
    0.61
    Chapter
    0.56
    Other
    0.53
    Document
    0.53
    Stream
    0.52
    ki
    0.49
    S
    0.49
    Data
    0.48
    OG
    0.47
    Lazy
    0.47
    POSITIVE LOGITS
     посвящён
    0.53
     splike
    0.52
     decía
    0.50
     сцена
    0.46
    🍸
    0.46
     vya
    0.46
     flavorful
    0.46
     liked
    0.46
     quinine
    0.46
     bary
    0.45
    Activations Density 0.005%

    No Known Activations