© 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. 47382
    Prev
    Next
    INDEX
    Explanations

    names of individuals

    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
     not
    -1.05
     armadura
    -0.91
     Destruction
    -0.89
     ilegal
    -0.89
    袂
    -0.82
     Meskipun
    -0.82
    мора
    -0.80
    Árbitro
    -0.80
     surprisingly
    -0.77
    Destruction
    -0.77
    POSITIVE LOGITS
    ಆ
    1.22
     bylo
    1.20
    alucía
    1.18
    ಅ
    1.18
    ïde
    1.09
     Zodiac
    1.07
    bbing
    1.03
     история
    1.02
    确实是
    1.02
    ⾯
    1.02
    Activations Density 0.137%

    No Known Activations