© 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. 7-GEMMASCOPE-2-RES-16K
    7. 11498
    Prev
    Next
    INDEX
    Explanations

    Rio Tinto and Rio de Janeiro

    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_7_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
    __(/*!
    3.02
    лта
    2.79
    izations
    2.70
    ución
    2.70
     Boxer
    2.68
    تي
    2.63
    магази
    2.60
    ކ
    2.57
    ोत्तम
    2.56
    𝐥
    2.53
    POSITIVE LOGITS
    ed
    3.46
    slope
    2.82
    ρα
    2.78
    ueda
    2.56
     slope
    2.54
    𝒎
    2.53
    בער
    2.51
    PhotoImage
    2.49
    MART
    2.48
    ра
    2.40
    Activations Density 0.001%

    No Known Activations