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. 29-GEMMASCOPE-2-RES-262K
    4. 962
    Prev
    Next
    INDEX
    Explanations

    phrases for examples

    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_29_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
    tabPage
    0.80
    ლები
    0.79
    㬰
    0.76
    новение
    0.72
     。,
    0.69
    ⎛
    0.68
    นะ
    0.68
    测评
    0.68
    谙
    0.68
    ievement
    0.67
    POSITIVE LOGITS
     bijvoorbeeld
    1.51
     например
    1.51
     Например
    1.49
     misalnya
    1.45
    例如
    1.43
    .
    1.39
     esimerkiksi
    1.39
     例如
    1.39
     example
    1.34
     Misalnya
    1.33
    Activations Density 0.083%

    No Known Activations