© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5023
    Prev
    Next
    INDEX
    Explanations

    discussion formatting

    np_acts-logits-general · gemini-2.5-flash-lite

    the presence of a floating-point number (a decimal numeral) in the text.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     PLAN
    0.80
    PY
    0.75
    lands
    0.73
    Ժ
    0.71
    이라
    0.70
    หลัง
    0.70
    บ
    0.70
     Pons
    0.69
    Ｐ
    0.69
    이랑
    0.68
    POSITIVE LOGITS
     globalization
    0.80
     riot
    0.70
     collusion
    0.70
     changes
    0.70
     anarchy
    0.70
     intelligence
    0.69
     goed
    0.68
     markup
    0.68
     interplay
    0.68
     poignant
    0.68
    Activations Density 0.000%

    No Known Activations