© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4269
    Prev
    Next
    INDEX
    Explanations

    via, proxy, terms, Pure, put, deep, asked

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_16k_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
     pemberian
    0.75
    关于
    0.66
    蔘
    0.66
     boissons
    0.64
     nyní
    0.64
    ILIA
    0.64
     estando
    0.63
    Waar
    0.63
    Mientras
    0.63
    >
    0.63
    POSITIVE LOGITS
    s
    0.93
    \})
    0.86
    sess
    0.83
    ደር
    0.82
    лыми
    0.80
     Hausdorff
    0.79
     SDW
    0.79
    ≤</
    0.78
     UTM
    0.77
     polynom
    0.77
    Activations Density 0.033%

    No Known Activations