© 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. 5192
    Prev
    Next
    INDEX
    Explanations

    plpgsql language code execution

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     better
    0.57
     attempting
    0.56
    々に
    0.56
     anyone
    0.56
    ُل
    0.54
    hanti
    0.54
     cycles
    0.52
    tox
    0.52
    ational
    0.50
    謢
    0.50
    POSITIVE LOGITS
    Primary
    0.62
     Primary
    0.60
    荣誉
    0.59
     नई
    0.56
     Closed
    0.56
     pendiente
    0.55
     PRIMARY
    0.55
     হাসি
    0.54
     setToDefault
    0.54
     VIN
    0.54
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.