© 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. 7-GEMMASCOPE-2-RES-16K
    7. 13576
    Prev
    Next
    INDEX
    Explanations

    research suggests

    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_7_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
    $^{
    3.00
    Reserv
    2.55
    Merc
    2.55
    W
    2.54
    ை
    2.54
     W
    2.44
     Fract
    2.40
     опо
    2.40
    өг
    2.37
     Cel
    2.36
    POSITIVE LOGITS
     jaki
    2.90
     asalamualaikum
    2.84
    ็จ
    2.63
    ğraf
    2.61
    walla
    2.60
    ی
    2.59
    品の
    2.47
    ración
    2.46
     spekt
    2.45
    utiérrez
    2.45
    Activations Density 0.014%

    No Known Activations