© 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. 34-GEMMASCOPE-RES-131K
    7. 30196
    Prev
    Next
    INDEX
    Explanations

    content management systems, linguistic, next

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    اعده
    -0.82
     commencement
    -0.79
    similar
    -0.75
     bezahlen
    -0.74
    вшись
    -0.74
     cowork
    -0.74
     fissures
    -0.74
    ّد
    -0.73
     gedung
    -0.73
     rosse
    -0.73
    POSITIVE LOGITS
     CMS
    0.93
     CM
    0.82
    Cms
    0.81
     Oyo
    0.75
     CMC
    0.71
    麝
    0.71
    ހ
    0.70
    antonio
    0.70
     dió
    0.69
     CMP
    0.68
    Activations Density 0.013%

    No Known Activations