© 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
    2. Gemma-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-65K
    4. 729
    Prev
    Next
    INDEX
    Explanations

    quantified parameters and categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ികളുടെ
    0.80
    akin
    0.78
     Архів
    0.76
    ικών
    0.74
    িনের
    0.72
     '${
    0.72
    annya
    0.72
    德
    0.72
    ικές
    0.71
    ডের
    0.70
    POSITIVE LOGITS
     Include
    0.90
     представля
    0.89
    Include
    0.87
     оформ
    0.84
    )
    0.81
     included
    0.81
     ممكن
    0.78
     include
    0.77
    ).
    0.77
    ):
    0.77
    Activations Density 0.602%

    No Known Activations