© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 10893
    Prev
    Next
    INDEX
    Explanations

    numerical star ratings and scores

    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
     ২৬
    1.30
     ২৮
    1.26
     ২৩
    1.23
     ৩৬
    1.19
     २
    1.18
     arriba
    1.17
     ৩৫
    1.17
     ২৪
    1.17
     ૩
    1.16
    এখন
    1.14
    POSITIVE LOGITS
     localities
    1.19
     vaak
    1.19
     mnoh
    1.18
     oftentimes
    1.17
     كلها
    1.11
     frequentemente
    1.10
     اکثر
    1.10
     대부분
    1.09
     diverse
    1.08
    หลาย
    1.08
    Activations Density 0.135%

    No Known Activations