© 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. 15020
    Prev
    Next
    INDEX
    Explanations

    frequent and consistent actions

    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
    一部分
    0.46
    <unused2130>
    0.46
    не
    0.45
    必要
    0.45
     کچھ
    0.44
     án
    0.43
     continuar
    0.42
     acond
    0.42
     lâu
    0.42
     🤗
    0.42
    POSITIVE LOGITS
     repeatedly
    0.80
    何度も
    0.75
    repeated
    0.75
     crises
    0.68
    繰り返
    0.68
     попы
    0.64
     repeated
    0.64
    反复
    0.61
    屢
    0.57
     earthquakes
    0.56
    Activations Density 0.048%

    No Known Activations