© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14807
    Prev
    Next
    INDEX
    Explanations

    python 'np' and 'pd' usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    𝒊
    2.36
    bo
    2.08
    inem
    2.07
    ੰਜਾਬ
    2.05
    اا
    2.00
    pets
    1.98
    𝒐
    1.94
    𝒆
    1.94
    subject
    1.94
    𝒂
    1.92
    POSITIVE LOGITS
    瞰
    2.88
    鹉
    2.58
    تالي
    2.56
    BigAutoField
    2.55
    тами
    2.52
     ?-
    2.35
    <bos>
    2.35
    亰
    2.31
    🐤
    2.28
    ตา
    2.25
    Activations Density 1.012%

    No Known Activations