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-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7498
    Prev
    Next
    INDEX
    Explanations

    orientation (portrait/landscape, photo, site, magnets, columns)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    raisal
    2.67
    hangi
    2.53
    শীল
    2.53
    스러운
    2.52
    ാല
    2.52
    л
    2.50
     gegenüber
    2.46
    Rightarrow
    2.45
    igraphy
    2.44
    多い
    2.44
    POSITIVE LOGITS
    й
    3.90
     именно
    2.80
    йся
    2.77
     саме
    2.73
    σετε
    2.69
    ی
    2.68
    ра
    2.67
    िजन
    2.66
    ന
    2.63
     hustle
    2.61
    Activations Density 0.014%

    No Known Activations