© 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-65K
    7. 762
    Prev
    Next
    INDEX
    Explanations

    response generation, negative elicit, inhibitory control

    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_65k_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
    C
    1.29
     собственного
    1.29
    тера
    1.28
     соответствующие
    1.27
    L
    1.21
    ágoras
    1.21
    对应的
    1.21
    D
    1.20
    mités
    1.19
    étera
    1.18
    POSITIVE LOGITS
     malfunction
    1.86
     manipulate
    1.82
     deformation
    1.79
     distinguish
    1.79
     ruler
    1.75
     イラスト
    1.74
     imprint
    1.73
     portray
    1.73
     fluctuation
    1.71
     differs
    1.71
    Activations Density 0.152%

    No Known Activations