© 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. 5797
    Prev
    Next
    INDEX
    Explanations

    share anything

    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
    ется
    2.34
    формация
    2.32
    enação
    2.28
     denitr
    2.27
     nomencl
    2.23
    इकिल
    2.23
     springfox
    2.18
    偎
    2.16
     ой
    2.15
     देओल
    2.14
    POSITIVE LOGITS
    fyp
    1.86
     lat
    1.76
    ால்
    1.74
    hari
    1.73
    룩
    1.73
    __(/*!
    1.73
    사회
    1.71
    בת
    1.69
    ghijklmnopqrst
    1.61
    domen
    1.61
    Activations Density 0.675%

    No Known Activations