© 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. 11859
    Prev
    Next
    INDEX
    Explanations

    mentions of Vicuna

    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
    sman
    2.79
    ের
    2.66
    ަރ
    2.29
    s
    2.27
    sle
    2.22
    ви
    2.19
    tre
    2.15
    erden
    2.10
    𝐢
    2.10
     Excell
    2.06
    POSITIVE LOGITS
    wish
    2.22
    Ꮮ
    2.05
    ਓ
    2.03
     résolution
    2.02
     geometría
    2.01
    clicked
    1.99
    Quarter
    1.99
     dissociate
    1.96
    ][[
    1.94
    ρ
    1.90
    Activations Density 0.546%

    No Known Activations