© 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. 10425
    Prev
    Next
    INDEX
    Explanations

    definitions and roles

    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
    '
    1.76
     됩니다
    1.54
     IM
    1.47
     INS
    1.47
     IN
    1.45
    IM
    1.44
    вача
    1.44
    꾼
    1.43
     된다
    1.43
    ﺤ
    1.43
    POSITIVE LOGITS
    ição
    1.97
     umum
    1.91
    generic
    1.82
    pthread
    1.79
     leche
    1.78
    iant
    1.76
     proportionally
    1.71
     parum
    1.71
     compr
    1.71
    escu
    1.71
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.