© 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-3-12B-IT
    3. 24-GEMMASCOPE-2-RES-262K
    4. 17673
    Prev
    Next
    INDEX
    Explanations

    they/them pronouns

    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_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
    它
    0.74
    ათ
    0.66
     его
    0.66
    <0x80>
    0.65
     його
    0.64
    icado
    0.63
     который
    0.62
    它的
    0.62
     Tiene
    0.62
    g
    0.60
    POSITIVE LOGITS
     вот
    0.74
    忱
    0.72
     وعلى
    0.70
     postaci
    0.70
    ్ఞ
    0.68
    這裡
    0.67
    ات
    0.66
    राट
    0.66
    යන්
    0.66
    تنا
    0.65
    Activations Density 0.002%

    No Known Activations