© 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. 1836
    Prev
    Next
    INDEX
    Explanations

    quantities and units

    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
    an
    2.14
    inqui
    1.86
    elves
    1.86
    ي
    1.80
    volved
    1.78
    eous
    1.76
    يّ
    1.74
    kannya
    1.73
    gery
    1.71
    ನ್ನು
    1.71
    POSITIVE LOGITS
    С
    1.83
    BU
    1.74
    VIAF
    1.61
    Cl
    1.60
    Е
    1.57
    UE
    1.55
    Jadi
    1.54
    E
    1.49
    ================
    1.48
    <_
    1.47
    Activations Density 0.004%

    No Known Activations