© 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. 47048
    Prev
    Next
    INDEX
    Explanations

    Create directory, color vision

    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
    Negative Logits
    左
    -0.81
     cortar
    -0.74
     rispar
    -0.69
    ᴋ
    -0.69
     przestr
    -0.68
    𝙋
    -0.68
     take
    -0.68
    简约
    -0.68
    kraine
    -0.67
    علم
    -0.67
    POSITIVE LOGITS
    🔶
    0.70
     делу
    0.69
    Crawler
    0.65
     esqu
    0.63
    hots
    0.62
     chez
    0.62
    zkod
    0.61
     Alha
    0.61
    therm
    0.61
     Vocal
    0.61
    Activations Density 0.063%

    No Known Activations