© 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. 15120
    Prev
    Next
    INDEX
    Explanations

    distances and locations

    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
     boulevard
    0.47
    rvGroup
    0.43
    停留
    0.43
    公园
    0.42
     便利
    0.42
    Coconut
    0.41
    选
    0.40
    保存
    0.40
    抔
    0.40
    bezier
    0.40
    POSITIVE LOGITS
     Moscow
    0.53
     दिल्‍ली
    0.48
     distant
    0.44
     Москва
    0.44
     Москве
    0.43
     fumble
    0.43
     puedo
    0.43
     London
    0.42
     відста
    0.42
     Detroit
    0.41
    Activations Density 0.037%

    No Known Activations