© 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-262K
    7. 4402
    Prev
    Next
    INDEX
    Explanations

    the fighting, the original, the bowel

    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
    не
    0.73
     Мето
    0.64
    нение
    0.64
    رض
    0.63
    რ
    0.61
    ることができます
    0.60
    न्देल
    0.60
    𝕠
    0.60
     metals
    0.59
     पर्यावरण
    0.59
    POSITIVE LOGITS
    '
    1.10
    .
    0.83
    ()'
    0.77
    ’
    0.71
    ell
    0.62
    ̇
    0.61
    _
    0.61
    '></
    0.59
    m
    0.58
    ;'
    0.57
    Activations Density 0.618%

    No Known Activations