© 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. 14759
    Prev
    Next
    INDEX
    Explanations

    assuming or related concepts

    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
     определён
    3.50
    вёр
    3.45
     своём
    3.16
     Всё
    3.15
    нё
    3.14
    ётся
    3.10
     идёт
    3.07
     ș
    3.06
     моём
    3.04
     тяжё
    3.02
    POSITIVE LOGITS
    Whilst
    2.93
     şi
    2.83
     (£
    2.58
     Whilst
    2.56
     specialising
    2.55
     £
    2.50
    colour
    2.44
     personalisation
    2.43
     minimising
    2.42
     fertiliser
    2.41
    Activations Density 0.223%

    No Known Activations