© 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. 12031
    Prev
    Next
    INDEX
    Explanations

    math and pi constants

    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
     FormsModule
    2.76
     служит
    2.50
    MgCl
    2.50
    <unused1873>
    2.45
    gameObjects
    2.44
    Ther
    2.43
    Filed
    2.41
    ⦖
    2.40
    زاز
    2.40
     evoked
    2.40
    POSITIVE LOGITS
    oon
    1.95
    ek
    1.85
    elijke
    1.83
    ebo
    1.83
    ed
    1.83
    eren
    1.82
    al
    1.81
    esen
    1.73
    hwar
    1.69
    eku
    1.69
    Activations Density 0.033%

    No Known Activations