© 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. 47214
    Prev
    Next
    INDEX
    Explanations

    questions or comments after article URL

    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
     Liang
    -0.78
    including
    -0.69
    chromatic
    -0.66
    Liang
    -0.66
    forEach
    -0.65
    ()))
    -0.65
    TRACK
    -0.63
     any
    -0.62
     Stripe
    -0.61
    Newly
    -0.61
    POSITIVE LOGITS
     perch
    0.73
    oscill
    0.73
    IOC
    0.72
    讼
    0.71
     記事
    0.70
     Bion
    0.70
    ISODE
    0.68
    Filing
    0.68
    Jau
    0.68
    Heel
    0.67
    Activations Density 0.052%

    No Known Activations