© 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. 12930
    Prev
    Next
    INDEX
    Explanations

    conversation and discussion

    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
    Negative Logits
    ean
    2.35
    gitian
    2.23
    ifika
    2.17
    дям
    2.14
    ling
    2.13
    lain
    2.07
    ۰۰
    2.04
    stehen
    2.02
    ଁ
    2.01
    WEBPACK
    2.01
    POSITIVE LOGITS
    <bos>
    2.36
    ere
    2.33
    ners
    2.27
    啬
    2.22
    会儿
    2.16
    ہ
    2.14
    ات
    2.14
    ঃখ
    2.13
    ْت
    2.13
    ̣t
    2.12
    Activations Density 0.269%

    No Known Activations