© 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. 695
    Prev
    Next
    INDEX
    Explanations

    data, segmentation, and code snippets

    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
    乳
    0.51
    badbreak
    0.50
     长
    0.49
    湖北
    0.46
     siguiente
    0.46
    NewUrl
    0.46
    <unused2>
    0.45
    无效
    0.45
    更换
    0.45
     الص
    0.44
    POSITIVE LOGITS
     If
    0.46
    配達
    0.42
     roy
    0.40
    KILL
    0.40
    ترین
    0.39
     میوز
    0.39
     konserv
    0.39
     pekan
    0.39
    If
    0.39
     Pran
    0.39
    Activations Density 0.011%

    No Known Activations