© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 5270
    Prev
    Next
    INDEX
    Explanations

    html code or technical terms

    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
     విడు
    0.77
     halten
    0.73
     selesai
    0.72
     ప్
    0.71
    hasil
    0.69
     geli
    0.68
     pl
    0.67
    큽
    0.67
    З
    0.67
    ܛ
    0.66
    POSITIVE LOGITS
    Hi
    0.76
    是对
    0.73
    gate
    0.67
     hi
    0.67
     বিবে
    0.66
    是一种
    0.65
    是對
    0.65
    hiya
    0.64
    爐
    0.63
     Hello
    0.63
    Activations Density 0.003%

    No Known Activations