© 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. 12568
    Prev
    Next
    INDEX
    Explanations

    units, dates, or technologies

    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
     ۔
    1.34
    жён
    1.29
     وهذا
    1.25
    вёр
    1.25
    чё
    1.19
    рё
    1.19
    .\
    1.17
    ৷
    1.17
    
    1.17
    ‪
    1.16
    POSITIVE LOGITS
     prioritise
    1.45
     recognising
    1.36
     Analyse
    1.26
     recognised
    1.24
     marginalised
    1.24
     ‘
    1.22
     recognisable
    1.20
     cosy
    1.19
     kajian
    1.19
     (‘
    1.19
    Activations Density 0.000%

    No Known Activations