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. 12400
    Prev
    Next
    INDEX
    Explanations

    team who, explicitly programming

    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
     ກ
    0.46
    sourceIP
    0.43
     Verständ
    0.43
     IIS
    0.42
    を高
    0.42
     ủy
    0.42
     AFP
    0.42
     ນ
    0.41
     GED
    0.41
    ಎಂ
    0.40
    POSITIVE LOGITS
    ів
    0.54
    ใ
    0.47
    scatterplot
    0.46
    orem
    0.45
    ppm
    0.45
     невро
    0.45
    泻
    0.45
    denum
    0.44
    ס
    0.43
     спектак
    0.43
    Activations Density 0.027%

    No Known Activations