© 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. 11750
    Prev
    Next
    INDEX
    Explanations

    recipes and python code structures

    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
    ياً
    1.25
    кове
    1.23
    ACT
    1.13
    اعت
    1.12
    ِي
    1.08
    يا
    1.07
    had
    1.06
    مرة
    1.05
    ادت
    1.05
    Im
    1.03
    POSITIVE LOGITS
     आपले
    1.28
     sullen
    1.26
     Stimmung
    1.20
    ปรุง
    1.19
     Strept
    1.18
    杓
    1.17
     dieting
    1.16
     ruhig
    1.16
     industrious
    1.15
    schnitt
    1.13
    Activations Density 0.001%

    No Known Activations