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
    3. 16-GEMMASCOPE-2-RES-16K
    4. 475
    Prev
    Next
    INDEX
    Explanations

    dangerous operation, receive your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tensor
    0.56
    asitriangular
    0.56
     seguramente
    0.54
     遅
    0.52
    servo
    0.52
     arxiv
    0.52
     SIAM
    0.52
    ².
    0.51
     quizá
    0.51
     ポイント
    0.50
    POSITIVE LOGITS
    ك
    0.56
    ام
    0.54
    I
    0.52
    ان
    0.52
    اي
    0.50
    య
    0.50
    ه
    0.50
    ਾ
    0.50
    د
    0.49
    リッジ
    0.49
    Activations Density 0.001%

    No Known Activations