© 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. 12-GEMMASCOPE-2-RES-16K
    7. 13398
    Prev
    Next
    INDEX
    Explanations

    summing increments

    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_12_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
    ных
    2.17
    ной
    2.13
    ين
    1.81
    िन
    1.79
    oon
    1.79
    ä
    1.79
    ार
    1.78
    ные
    1.76
    eni
    1.75
    iv
    1.74
    POSITIVE LOGITS
    ف
    2.42
    ج
    1.93
    ق
    1.86
    いろんな
    1.71
    ح
    1.70
    cą
    1.55
    ه
    1.51
    겪
    1.48
    лно
    1.48
    年的
    1.45
    Activations Density 0.027%

    No Known Activations