© 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. 10685
    Prev
    Next
    INDEX
    Explanations

    website topics

    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
    It
    1.12
    There
    1.05
    ユーザ
    0.98
    إ
    0.97
    The
    0.96
    ee
    0.95
    Ee
    0.95
    You
    0.95
    某
    0.91
    Cheers
    0.91
    POSITIVE LOGITS
     windfall
    1.30
    faceted
    1.25
     titan
    1.22
     deepen
    1.22
     stemming
    1.22
     densely
    1.21
    <unused470>
    1.21
    <unused1814>
    1.20
     ousted
    1.20
     quartet
    1.18
    Activations Density 0.028%

    No Known Activations