© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 480
    Prev
    Next
    INDEX
    Explanations

    Here are

    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
     کنم
    0.89
     Dí
    0.88
     رسید
    0.75
    滁
    0.75
     Beet
    0.73
    oured
    0.71
     darle
    0.71
     Doodle
    0.71
    托管
    0.70
    噉
    0.69
    POSITIVE LOGITS
    inac
    1.61
    <unused2222>
    1.59
    <unused2120>
    1.54
    gister
    1.54
    <unused2223>
    1.54
    onio
    1.51
    alista
    1.50
    quirements
    1.50
    onia
    1.50
    <unused89>
    1.49
    Activations Density 0.793%

    No Known Activations