© 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. 9430
    Prev
    Next
    INDEX
    Explanations

    that's it

    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
     chromospheric
    0.62
     nmea
    0.59
     случи
    0.58
     deswegen
    0.57
     rappro
    0.56
    čko
    0.56
     coursework
    0.56
    তামূলক
    0.55
    액
    0.55
    मेलन
    0.55
    POSITIVE LOGITS
     Pretty
    0.58
    Powerful
    0.57
     pretty
    0.56
    Yup
    0.55
    essentially
    0.54
    ty
    0.54
    Pretty
    0.54
    確か
    0.54
    powerful
    0.54
     precisely
    0.53
    Activations Density 0.052%

    No Known Activations