© 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. 12-GEMMASCOPE-2-RES-262K
    4. 5630
    Prev
    Next
    INDEX
    Explanations

    american federation

    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
    LAY
    0.73
    ED
    0.71
    Με
    0.71
    А
    0.65
     procurar
    0.63
    ES
    0.62
     reactivation
    0.62
    ہنی
    0.61
    EVEN
    0.61
    OGRAPHY
    0.59
    POSITIVE LOGITS
    ्स
    1.29
    ੀ
    1.02
    oo
    0.96
    er
    0.91
    ofthe
    0.91
    in
    0.84
    اً
    0.83
    land
    0.81
    티
    0.81
    of
    0.80
    Activations Density 0.069%

    No Known Activations