© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 6779
    Prev
    Next
    INDEX
    Explanations

    provides functions or import

    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
    t
    1.37
    al
    1.26
    ing
    1.15
    et
    1.15
    ming
    1.15
    f
    1.11
    el
    1.11
    eting
    1.04
    ف
    1.03
    of
    1.03
    POSITIVE LOGITS
    rieden
    1.84
     다양한
    1.84
    !("{
    1.77
     そして
    1.76
     이러한
    1.75
     大型
    1.75
     고급
    1.72
    𒈗
    1.72
     じゃん
    1.72
    padă
    1.71
    Activations Density 0.152%

    No Known Activations