© 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. 13795
    Prev
    Next
    INDEX
    Explanations

    command prompt

    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
     (
    1.55
    1.52
    (
    1.34
    ,
    1.25
    /
    1.24
    *
    1.23
     [
    1.10
    -
    1.07
     *
    1.07
    =
    1.06
    POSITIVE LOGITS
    pointB
    1.99
    秙
    1.93
    enamefont
    1.91
    䣷
    1.87
    媝
    1.81
    玝
    1.79
    龺
    1.79
    乨
    1.78
    軐
    1.78
    𒅴
    1.76
    Activations Density 0.173%

    No Known Activations