© 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. 7-GEMMASCOPE-2-RES-16K
    7. 11854
    Prev
    Next
    INDEX
    Explanations

    unit testing

    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
     molte
    2.43
     ottimo
    2.42
     ácido
    2.41
     numerose
    2.39
     provare
    2.38
     proveedor
    2.37
     envío
    2.35
    <unused1401>
    2.33
     asociación
    2.33
     próprias
    2.32
    POSITIVE LOGITS
    с
    1.53
     change
    1.47
    os
    1.42
    a
    1.41
    posed
    1.40
    e
    1.38
    ons
    1.36
     plan
    1.35
    o
    1.34
    olateral
    1.33
    Activations Density 0.037%

    No Known Activations