© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 11532
    Prev
    Next
    INDEX
    Explanations

    code function syntax

    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
     of
    1.84
     with
    1.68
     for
    1.66
     in
    1.55
     and
    1.54
     to
    1.36
    .
    1.30
    ,
    1.30
     from
    1.29
     throughout
    1.29
    POSITIVE LOGITS
     másik
    2.14
     próprio
    2.09
     potência
    2.06
     vuelva
    2.03
     espaço
    2.02
     luogo
    2.02
     irmão
    1.97
     második
    1.96
     distância
    1.92
     quello
    1.91
    Activations Density 0.068%

    No Known Activations