© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9545
    Prev
    Next
    INDEX
    Explanations

    view resolution

    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_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     bioge
    0.67
     semidefinite
    0.66
     bokeh
    0.65
     spazio
    0.65
     trasc
    0.63
     nouns
    0.63
     LHS
    0.63
    湋
    0.62
     PROC
    0.61
     ambiental
    0.61
    POSITIVE LOGITS
    erView
    0.89
     View
    0.82
     VIEW
    0.70
    ü
    0.70
    View
    0.69
    たり
    0.68
    view
    0.67
     view
    0.67
    न्
    0.67
    眦
    0.66
    Activations Density 0.100%

    No Known Activations