© 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. 23
    Prev
    Next
    INDEX
    Explanations

    is followed by definition

    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
    }+
    0.37
    ers
    0.36
    ){
    0.36
    )+
    0.34
    Both
    0.33
    </tr>
    0.32
    However
    0.32
    Eas
    0.31
    )-
    0.30
    Many
    0.30
    POSITIVE LOGITS
     berupa
    0.76
     twofold
    0.69
     comprised
    0.63
     threefold
    0.60
     عباره
    0.58
     simply
    0.55
     akin
    0.55
     dictated
    0.55
     связано
    0.54
     মূলত
    0.54
    Activations Density 2.068%

    No Known Activations