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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1873
    Prev
    Next
    INDEX
    Explanations

    GPT-4

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     डेढ़
    0.69
    ১৫
    0.67
     ۱۵
    0.65
    ('../../
    0.62
     XIII
    0.60
     ৭৫
    0.58
     ۱۳
    0.58
    fgets
    0.57
     quinze
    0.57
    லிக்க
    0.56
    POSITIVE LOGITS
     FOUR
    3.43
    ４
    3.38
    4
    3.36
     Four
    3.34
     Fourth
    3.34
    四
    3.33
     four
    3.28
     fours
    3.25
    four
    3.22
     fourth
    3.21
    Activations Density 1.395%

    No Known Activations