© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 12186
    Prev
    Next
    INDEX
    Explanations

    you've got

    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
     constituer
    1.17
     construire
    1.08
     abertura
    1.08
     Pra
    1.05
    এ
    1.04
     dialogo
    1.03
     konusu
    1.02
     costruire
    1.02
     Apartment
    1.01
     dinâmica
    1.01
    POSITIVE LOGITS
    ffd
    1.25
    UREMENT
    1.20
    DBES
    1.17
     jerk
    1.15
     caterpillars
    1.14
    fling
    1.12
    燜
    1.11
    URED
    1.11
    фель
    1.11
     anthrac
    1.10
    Activations Density 0.054%

    No Known Activations