© 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. 7-GEMMASCOPE-2-RES-16K
    7. 10947
    Prev
    Next
    INDEX
    Explanations

    sketching and drawing visual art

    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_7_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
    ukai
    1.95
    وء
    1.68
    omnia
    1.67
    ల్ల
    1.63
    akang
    1.61
    ্য
    1.61
    Ğ
    1.60
    ী
    1.57
     fréquent
    1.57
     défaut
    1.57
    POSITIVE LOGITS
    נען
    2.36
    掍
    2.33
    ပြင်
    2.22
    sbin
    2.11
    fähig
    2.07
     वनस्प
    2.07
     번째
    2.05
    maket
    2.05
    frameN
    2.04
    ˖
    2.04
    Activations Density 0.115%

    No Known Activations