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. 31-GEMMASCOPE-2-RES-16K
    4. 11639
    Prev
    Next
    INDEX
    Explanations

    define what's next

    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_16k_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
    膑
    0.68
     effectuer
    0.67
     увеличения
    0.67
    ፫
    0.66
     =
    0.64
     verschill
    0.64
     различ
    0.64
     exhort
    0.63
     ежедневно
    0.63
     is
    0.62
    POSITIVE LOGITS
    it
    1.04
    定義
    0.95
    in
    0.92
    an
    0.92
    as
    0.91
    defined
    0.89
    ん
    0.89
    is
    0.89
    Defined
    0.88
    Defining
    0.86
    Activations Density 0.130%

    No Known Activations