© 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. 43420
    Prev
    Next
    INDEX
    Explanations

    African American origins and descent

    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
    am
    1.73
    ap
    1.66
    um
    1.66
    al
    1.64
    ak
    1.61
    ot
    1.59
    ia
    1.52
    ü
    1.52
    ie
    1.51
    いま
    1.49
    POSITIVE LOGITS
    ਨ
    1.70
    此之外
    1.64
     metabolized
    1.64
     aloud
    1.63
     glyc
    1.59
     analyzed
    1.54
     instigated
    1.52
     subjecting
    1.52
     emphasized
    1.48
    도는
    1.48
    Activations Density 0.002%

    No Known Activations