© 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-3-270M
    3. 15-GEMMASCOPE-2-RES-16K
    4. 3783
    Prev
    Next
    INDEX
    Explanations

    alternatives or not sticking to one

    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
    ленно
    1.18
    efully
    1.17
    璋
    1.10
    temperatur
    1.06
    réd
    1.01
    бою
    0.99
    luent
    0.97
    wartz
    0.95
     antiquity
    0.95
    UGHT
    0.92
    POSITIVE LOGITS
    SIMPLEX
    1.50
    Mapa
    1.48
    停车
    1.44
    ຕ
    1.44
     YoY
    1.42
     Expedia
    1.41
     аксе
    1.41
    APOLIS
    1.41
    っきり
    1.40
     Mapa
    1.37
    Activations Density 0.023%

    No Known Activations