© 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
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1781
    Prev
    Next
    INDEX
    Explanations

    links and URLs

    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_65k_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
     form
    1.20
     on
    1.16
     coming
    1.15
     e
    1.11
     pick
    1.10
     up
    1.06
     hardening
    1.05
     all
    1.05
     unt
    1.04
     apart
    1.03
    POSITIVE LOGITS
    azienda
    1.62
    Tools
    1.58
     przedsiębior
    1.58
    endidikan
    1.57
     intitulé
    1.56
     minuman
    1.54
     escolas
    1.53
     coordinador
    1.52
    ہ
    1.52
    ikiran
    1.52
    Activations Density 0.149%

    No Known Activations