© 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
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 4465
    Prev
    Next
    INDEX
    Explanations

    lists of points

    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_262k_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
    <0x90>
    2.05
    et
    1.95
    <0xA2>
    1.72
    <0xB8>
    1.66
    و
    1.66
    ется
    1.65
    n
    1.62
    al
    1.61
    اد
    1.56
    s
    1.51
    POSITIVE LOGITS
     enkelt
    1.66
     esteemed
    1.58
     backlit
    1.52
     wacky
    1.46
     astrophysical
    1.41
     turbulent
    1.39
     repur
    1.39
     knot
    1.38
     hectic
    1.38
     manpower
    1.37
    Activations Density 0.021%

    No Known Activations