© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38538
    Prev
    Next
    INDEX
    Explanations

    legality and prohibition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ‘‘
    -1.70
     rowspan
    -1.64
     tradicional
    -1.53
    salms
    -1.52
    htb
    -1.52
    ?
    -1.52
     

    -1.51
     another
    -1.48
     alcance
    -1.46
    StoryboardSegue
    -1.46
    POSITIVE LOGITS
     for
    1.84
     cek
    1.68
     these
    1.58
    6
    1.55
     but
    1.55
    4
    1.52
     saus
    1.49
    ❓
    1.49
     diny
    1.47
     lomba
    1.47
    Activations Density 0.064%

    No Known Activations