© 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. 6045
    Prev
    Next
    INDEX
    Explanations

    role or persona descriptions

    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
     “
    1.88
     C
    1.72
     P
    1.67
     The
    1.67
     Big
    1.64
     In
    1.62
     S
    1.59
     s
    1.58
     E
    1.57
     ‘
    1.57
    POSITIVE LOGITS
    escol
    2.54
    ríklad
    2.52
    ihat
    2.48
    enangan
    2.48
    ettha
    2.48
    archiwizowane
    2.45
    atthane
    2.43
    <unused1622>
    2.40
    aço
    2.40
    encher
    2.40
    Activations Density 0.259%

    No Known Activations