© 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. 41616
    Prev
    Next
    INDEX
    Explanations

    Failed at, into plugin

    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
    ა
    0.56
    시
    0.53
    아
    0.49
    고사
    0.48
    畯
    0.48
    칭
    0.47
    جد
    0.47
    에
    0.47
    ة
    0.46
    ᅦ
    0.46
    POSITIVE LOGITS
     m
    0.52
     influence
    0.52
     people
    0.48
    inks
    0.47
     м
    0.47
    la
    0.47
     twenty
    0.47
    rv
    0.46
     engineers
    0.46
    ologis
    0.46
    Activations Density 0.001%

    No Known Activations