Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 119900
    Prev
    Next
    INDEX
    Explanations

    Python script or file

    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_40_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
     интегра
    0.45
     минима
    0.42
    恢復
    0.40
     лока
    0.40
     recovered
    0.39
     норма
    0.39
     визуа
    0.39
    ግ
    0.39
     recovering
    0.39
    積分
    0.39
    POSITIVE LOGITS
    uesa
    0.42
    uri
    0.39
    atsi
    0.38
    流行的
    0.38
    category
    0.38
    autres
    0.38
     puiss
    0.38
     alterar
    0.38
    searchResults
    0.38
     frequently
    0.37
    Activations Density 0.003%

    No Known Activations