© 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. 125278
    Prev
    Next
    INDEX
    Explanations

    Social Hierarchy, Innovation

    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
     Reth
    0.49
     solvents
    0.48
     Hand
    0.47
    פ
    0.46
    כ
    0.46
    𝜁
    0.45
     ज
    0.45
    ער
    0.45
     dams
    0.45
    aktion
    0.45
    POSITIVE LOGITS
     العزيز
    0.42
    します
    0.41
    네요
    0.40
     заместитель
    0.40
     flourish
    0.39
     അരി
    0.39
    glise
    0.38
    loir
    0.38
    lightbox
    0.38
    渺
    0.38
    Activations Density 0.003%

    No Known Activations