© 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. 25300
    Prev
    Next
    INDEX
    Explanations

    creating new orders

    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
     Lebensmittel
    0.38
     Bergeron
    0.38
     leukocyte
    0.37
    嘮
    0.36
     Bragg
    0.35
     Boltzmann
    0.35
     drawstring
    0.35
     Granger
    0.34
     Begegn
    0.34
     Conducting
    0.34
    POSITIVE LOGITS
    😀
    0.43
    获取
    0.41
    实时
    0.40
    倸
    0.39
    创建
    0.39
    că
    0.39
     pentru
    0.39
    ərbay
    0.39
     для
    0.38
     fro
    0.38
    Activations Density 0.001%

    No Known Activations