© 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. 7-GEMMASCOPE-2-RES-16K
    7. 1723
    Prev
    Next
    INDEX
    Explanations

    code blocks

    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_7_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
    erden
    2.71
    ဟုတ်
    2.66
    yim
    2.61
    ી
    2.53
    加坡
    2.52
    ০
    2.49
    יים
    2.43
    dì
    2.43
    toctree
    2.43
    י
    2.38
    POSITIVE LOGITS
    ew
    2.26
    at
    2.13
    eng
    1.93
    inuous
    1.84
    chez
    1.82
    дії
    1.81
    igr
    1.80
    entire
    1.78
    нов
    1.77
    ig
    1.76
    Activations Density 0.057%

    No Known Activations