© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 15295
    Prev
    Next
    INDEX
    Explanations

    into cells, signal fat

    np_acts-logits-general · gemini-2.5-flash-lite

    mentioning antibody, chemical, medicine, dyes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_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
     arkadaşlar
    0.46
     pouvant
    0.44
     arkadaş
    0.44
    满满
    0.44
     Nada
    0.43
    ”
    0.43
     antics
    0.43
    CreateParams
    0.43
    ونة
    0.42
     właścic
    0.41
    POSITIVE LOGITS
    medicine
    0.49
    ുവ
    0.48
     ಹೆಚ್ಚು
    0.46
     சுற்றுச்சூழ
    0.46
     હશે
    0.45
     य
    0.45
    रीय
    0.45
    Sorter
    0.44
     શિક્ષણ
    0.44
    CATEGORY
    0.43
    Activations Density 0.012%

    No Known Activations