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
    3. 16-GEMMASCOPE-2-RES-16K
    4. 147
    Prev
    Next
    INDEX
    Explanations

    avoiding false, then take

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ’
    0.68
    ן
    0.57
    شون
    0.55
    uramente
    0.55
    vio
    0.54
     همچنین
    0.54
    an
    0.54
    ুকে
    0.53
     Universitas
    0.52
     Mumbai
    0.52
    POSITIVE LOGITS
    {
    0.60
    Т
    0.60
    白
    0.57
    ╱
    0.53
    蚁
    0.51
    ESS
    0.49
    WWW
    0.49
    ,
    0.48
     pairs
    0.48
    向き
    0.47
    Activations Density 0.000%

    No Known Activations