© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13374
    Prev
    Next
    INDEX
    Explanations

    public, followed by notice, networks, or appearances

    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
    ed
    2.31
    ě
    2.21
    ძლიათ
    2.14
    getSheet
    2.14
    zag
    2.06
    waitUntil
    2.01
    ebu
    1.98
    ouched
    1.94
    ନ୍ଦ
    1.92
     Inhib
    1.84
    POSITIVE LOGITS
    此之外
    3.08
    䒑
    2.77
    tan
    2.56
    ੀ
    2.51
    مي
    2.50
    т
    2.50
    اا
    2.41
    త్రిక
    2.36
    luss
    2.32
    تن
    2.32
    Activations Density 0.161%

    No Known Activations