© 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. 6881
    Prev
    Next
    INDEX
    Explanations

    provides or ensures functions

    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
    巴
    1.18
    아이
    1.17
    팟
    1.16
    辭
    1.14
     boosted
    1.13
     걸
    1.11
     الشريط
    1.10
     紅
    1.10
     白
    1.09
     아이
    1.09
    POSITIVE LOGITS
     encarg
    1.71
     respons
    1.59
     responsibility
    1.52
     roles
    1.51
     role
    1.47
     ansvar
    1.45
    负责
    1.44
     rôle
    1.43
    役割
    1.43
     encargado
    1.43
    Activations Density 0.328%

    No Known Activations