© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 6322
    Prev
    Next
    INDEX
    Explanations

    cool compress or water

    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_13_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
    ුව
    1.59
    PORTS
    1.56
    첸
    1.47
    ותו
    1.41
     немає
    1.37
    뉴
    1.37
     سونے
    1.36
    ει
    1.35
    ڈنگ
    1.33
     отделения
    1.33
    POSITIVE LOGITS
    मर्श
    1.73
    apple
    1.49
    apagos
    1.48
    iguity
    1.45
    emper
    1.45
    सर्जन
    1.45
    蜓
    1.41
    atherine
    1.41
     supernatant
    1.40
    মিক্যাল
    1.40
    Activations Density 0.001%

    No Known Activations