© 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. 4924
    Prev
    Next
    INDEX
    Explanations

    once i have, then personalized

    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
    гов
    1.27
    fullName
    1.25
    listdir
    1.24
    svet
    1.20
    [![
    1.20
    عداد
    1.19
    欢迎
    1.19
    emaakt
    1.16
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.16
    ↵↵↵↵↵↵↵↵↵↵↵↵
    1.16
    POSITIVE LOGITS
     Leibn
    1.16
    asă
    1.12
    aš
    1.11
     stretchy
    1.11
    pción
    1.06
     enigma
    1.05
    プレー
    1.04
     dels
    1.02
     geldiniz
    1.02
    ulers
    1.01
    Activations Density 0.064%

    No Known Activations