© 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
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13771
    Prev
    Next
    INDEX
    Explanations

    how to run code

    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
     intelligence
    1.12
     Host
    1.07
     Hain
    1.07
     Intelligence
    1.03
     hostname
    1.01
     largest
    1.00
     trips
    0.99
     빌
    0.99
    گاہ
    0.98
     Trip
    0.98
    POSITIVE LOGITS
     decoración
    1.46
     décoration
    1.45
     decoração
    1.45
     приготов
    1.43
     juguete
    1.43
     decorar
    1.40
     enca
    1.39
     déco
    1.37
     dekor
    1.35
     estet
    1.35
    Activations Density 0.006%

    No Known Activations