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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 8503
    Prev
    Next
    INDEX
    Explanations

    cooked to pink or brown

    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
    sembling
    1.09
     outnumbered
    1.07
     fodder
    1.06
     shepherd
    1.05
     assembling
    1.02
    止
    0.97
     entour
    0.95
     heterogeneous
    0.94
     calam
    0.94
     assembled
    0.94
    POSITIVE LOGITS
    إ
    1.24
     فلا
    1.17
     பெண்ண
    1.16
     الإص
    1.14
     إنشاء
    1.14
    Girls
    1.12
     إص
    1.11
    Compliance
    1.11
    اکہ
    1.10
    Engagement
    1.08
    Activations Density 0.000%

    No Known Activations