© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 112499
    Prev
    Next
    INDEX
    Explanations

    prophecy, whispers, folklore

    np_acts-logits-general · gemini-2.5-flash-lite

    the starts of quoted dialogue, especially opening quotation marks and the beginning of spoken lines.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     Partnerships
    0.43
    玩法
    0.43
     Generators
    0.43
     пье
    0.42
    膈
    0.42
    amides
    0.40
    Standalone
    0.40
     মানে
    0.40
    缝
    0.39
    rollees
    0.39
    POSITIVE LOGITS
     szczeg
    0.47
     hereto
    0.45
     searching
    0.44
    search
    0.43
    自分の
    0.43
     harboring
    0.42
     cher
    0.41
    forder
    0.41
    slope
    0.41
    գ
    0.41
    Activations Density 0.009%

    No Known Activations