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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12414
    Prev
    Next
    INDEX
    Explanations

    rating 5 stars

    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
    Numeric
    0.43
     numeric
    0.43
    numeric
    0.42
     degr
    0.42
     l
    0.41
    []');
    0.40
    范围
    0.40
     roughly
    0.39
    三
    0.39
     tile
    0.39
    POSITIVE LOGITS
     initialized
    0.39
     बहनों
    0.38
     නව
    0.38
     Materialien
    0.38
     explicitly
    0.37
    বারের
    0.37
     Activated
    0.36
    ्ठा
    0.36
     الجديدة
    0.36
    пры
    0.36
    Activations Density 0.041%

    No Known Activations