© 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
    2. Gemma-3-1B
    3. 22-GEMMASCOPE-2-RES-16K
    4. 9511
    Prev
    Next
    INDEX
    Explanations

    moving beyond

    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
     [
    0.77
     Neither
    0.75
     [.
    0.73
     /
    0.70
    ”
    0.70
    "
    0.70
     (?)
    0.70
     rather
    0.69
    www
    0.67
     both
    0.67
    POSITIVE LOGITS
    <unused1520>
    1.74
    <unused1531>
    1.74
    ține
    1.72
    <unused1526>
    1.71
    <unused1462>
    1.69
    ținut
    1.69
    <unused1516>
    1.68
    <unused1595>
    1.68
    <unused1533>
    1.67
    <unused1581>
    1.67
    Activations Density 0.958%

    No Known Activations