© 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. 5435
    Prev
    Next
    INDEX
    Explanations

    function arguments and data types

    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
     blossoms
    1.37
     tipped
    1.37
     podrás
    1.34
     podrán
    1.31
    <unused820>
    1.27
     Dink
    1.27
     Brows
    1.26
     capturedPlayer
    1.26
    <unused1934>
    1.25
    㓦
    1.24
    POSITIVE LOGITS
     боя
    0.98
    0.93
     I
    0.93
    вичай
    0.88
    少了
    0.82
     QT
    0.76
    anoate
    0.76
    econ
    0.76
    akwa
    0.74
    qh
    0.74
    Activations Density 0.036%

    No Known Activations