© 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. 13977
    Prev
    Next
    INDEX
    Explanations

    identifiers followed by colon

    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
    ==
    0.81
    ()==
    0.80
     ==
    0.78
    )==
    0.78
    ']==
    0.74
    Logic
    0.71
    ]==
    0.69
    ==(
    0.67
    logic
    0.61
    !=
    0.61
    POSITIVE LOGITS
     gud
    0.68
     multib
    0.61
    ikap
    0.59
     entonces
    0.57
     existir
    0.56
    roon
    0.56
     polite
    0.55
     Barbar
    0.55
     khud
    0.55
     thì
    0.54
    Activations Density 0.000%

    No Known Activations