© 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. 13448
    Prev
    Next
    INDEX
    Explanations

    girl, guitar, design engineer

    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
    ’
    0.85
     otras
    0.77
     otros
    0.73
    বাত
    0.71
    '
    0.70
    としている
    0.70
     समृद्धि
    0.70
    прави
    0.69
    صح
    0.69
     B
    0.69
    POSITIVE LOGITS
    celain
    0.98
    يًا
    0.92
    zaXRvcn
    0.90
    ي
    0.90
    િક
    0.89
    ură
    0.86
    шня
    0.86
    पत्र
    0.85
     হ্
    0.84
    eburger
    0.83
    Activations Density 0.001%

    No Known Activations