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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 45
    Prev
    Next
    INDEX
    Explanations

    cannot or not statements

    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
     লিও
    0.86
     Borges
    0.77
     gren
    0.73
    ysen
    0.73
    Goss
    0.71
     verg
    0.70
     -&
    0.70
     নিষেধ
    0.70
    leet
    0.70
    ở
    0.69
    POSITIVE LOGITS
    {
    2.13
     {
    1.56
    {-
    1.39
    {(
    1.39
    {.
    1.36
    {'
    1.33
    {"
    1.29
    {[
    1.24
    {*
    1.23
    {\
    1.23
    Activations Density 0.787%

    No Known Activations