© 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. 137
    Prev
    Next
    INDEX
    Explanations

    to Thing

    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
     
    0.46
     propositional
    0.45
     substrings
    0.43
     `=`
    0.42
     effettu
    0.42
     binomial
    0.42
     antider
    0.41
     
    0.41
     anemia
    0.41
     checkboxes
    0.41
    POSITIVE LOGITS
    H
    0.46
    K
    0.46
    Sh
    0.42
    M
    0.41
    T
    0.41
     Sh
    0.41
    Ar
    0.40
    C
    0.40
    Others
    0.38
    L
    0.38
    Activations Density 0.894%

    No Known Activations