© 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. 902
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ⵄ
    1.55
     ingresos
    1.47
     kaliteli
    1.45
     scopo
    1.43
     পরিমান
    1.42
     governo
    1.41
     domicilio
    1.40
     realizzazione
    1.39
    ᓘ
    1.38
     metà
    1.37
    POSITIVE LOGITS
     that
    2.14
     which
    2.06
     whose
    1.71
    which
    1.63
    that
    1.59
     who
    1.48
    ,
    1.43
     whereby
    1.42
     والتي
    1.35
     with
    1.32
    Activations Density 4.045%

    No Known Activations