© 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-65K
    7. 12718
    Prev
    Next
    INDEX
    Explanations

    updates, electrify, vacuum, chess, limestone, tape

    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_65k_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
    ุปกรณ์
    0.48
     област
    0.46
    噱
    0.46
     аген
    0.44
     haki
    0.43
    约翰
    0.43
    ิร์
    0.42
    枻
    0.42
    蒺
    0.41
    יל
    0.41
    POSITIVE LOGITS
    structure
    0.41
     routinely
    0.39
     geology
    0.39
    生の
    0.38
    history
    0.38
    ponsor
    0.36
    record
    0.35
    journ
    0.35
    rule
    0.35
     undisturbed
    0.35
    Activations Density 0.015%

    No Known Activations