© 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. 13640
    Prev
    Next
    INDEX
    Explanations

    C++ NATO reports double customizable

    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
    .
    1.81
     lest
    1.52
     in
    1.50
    !
    1.44
     for
    1.40
     to
    1.40
     that
    1.37
    ,
    1.37
     about
    1.36
     when
    1.33
    POSITIVE LOGITS
     berusia
    1.77
    ⵄ
    1.68
    Số
    1.65
     menjalani
    1.65
    栦
    1.65
     terdiri
    1.63
    ⵚ
    1.63
     Đúng
    1.61
     Còn
    1.61
    সিসি
    1.60
    Activations Density 0.000%

    No Known Activations