© 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. 10474
    Prev
    Next
    INDEX
    Explanations

    or, or, or

    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
    وذ
    1.45
    zunehmen
    1.42
    lös
    1.37
    ęb
    1.36
    ,{\
    1.35
    stol
    1.35
    diameter
    1.35
    شف
    1.34
     dissociation
    1.30
     disintegration
    1.30
    POSITIVE LOGITS
    如果
    1.25
     хочу
    1.21
     quero
    1.16
     не
    1.13
     Rui
    1.12
     nuo
    1.12
    彡
    1.11
     moje
    1.11
    自从
    1.11
     minhas
    1.10
    Activations Density 0.000%

    No Known Activations