© 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. 11001
    Prev
    Next
    INDEX
    Explanations

    property, body, economic, portfolio, tone

    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
     empathetic
    1.09
     BP
    1.07
     brutality
    1.06
     BN
    1.06
     BCR
    1.03
    oyeva
    1.02
    Bm
    1.01
    猁
    1.00
    borderwidth
    1.00
    bdb
    0.99
    POSITIVE LOGITS
     gennem
    0.98
    してきた
    0.79
    ッキ
    0.79
     выпол
    0.79
     além
    0.79
    等等
    0.78
     tudo
    0.78
    やら
    0.77
    해도
    0.77
     raiz
    0.77
    Activations Density 0.050%

    No Known Activations