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-65K
    4. 41365
    Prev
    Next
    INDEX
    Explanations

    function return values and errors

    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_65k_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
     whether
    0.99
     if
    0.99
     符合
    0.94
     belongs
    0.90
    >),
    0.90
     אם
    0.90
    {
    0.89
    .])
    0.88
     supposing
    0.88
    }={
    0.88
    POSITIVE LOGITS
     !_
    1.42
     !
    1.40
    /*
    1.36
    !"
    1.31
     !"
    1.29
    !」
    1.20
     !$
    1.19
     !”
    1.14
     !(
    1.14
    !
    1.12
    Activations Density 0.016%

    No Known Activations