© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 852
    Prev
    Next
    INDEX
    Explanations

    helpline numbers

    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_22_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
    <u>
    1.08
    <em>
    0.99
    ală
    0.97
    <i>
    0.95
    <sub>
    0.95
    adanam
    0.90
    <sup>
    0.88
    adhatu
    0.87
    <strong>
    0.84
    banam
    0.83
    POSITIVE LOGITS
     There
    2.54
     These
    2.52
     This
    2.50
     The
    2.35
     However
    2.32
     We
    2.29
     Why
    2.27
     Although
    2.27
     What
    2.25
     How
    2.22
    Activations Density 7.397%

    No Known Activations