© 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. 3917
    Prev
    Next
    INDEX
    Explanations

    formal and technical descriptions

    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
     inappropriate
    0.46
     unacceptable
    0.44
    或者是
    0.42
     زائدا
    0.40
    ">,</
    0.39
    顽
    0.39
    或者
    0.39
     inappropriately
    0.39
     hoặc
    0.38
    izontally
    0.38
    POSITIVE LOGITS
    calcular
    0.50
     calculer
    0.49
    ক্ষেপে
    0.46
     ahorrar
    0.46
     saves
    0.45
     Saves
    0.45
    mejor
    0.45
     экономи
    0.42
    얼
    0.41
     económicas
    0.41
    Activations Density 0.011%

    No Known Activations