© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 4548
    Prev
    Next
    INDEX
    Explanations

    code blocks, commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    cerpt
    1.75
     Trinidad
    1.69
     mano
    1.68
     Prospect
    1.67
     Ebene
    1.67
     Cove
    1.67
     opportune
    1.66
    搧
    1.66
    orov
    1.62
    çu
    1.61
    POSITIVE LOGITS
    =\{\
    1.49
    +[
    1.48
    \{\
    1.43
    {"
    1.24
    ätten
    1.17
    \{
    1.16
    ステン
    1.14
     צו
    1.13
    hite
    1.13
    Marker
    1.12
    Activations Density 0.016%

    No Known Activations