© 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. 22-GEMMASCOPE-RES-131K
    7. 127666
    Prev
    Next
    INDEX
    Explanations

    numbers in parentheses

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     in
    -2.05
     (
    -1.95
     from
    -1.88
    ˂
    -1.87
    Despite
    -1.85
     веке
    -1.83
     that
    -1.80
     after
    -1.80
    Usually
    -1.79
     because
    -1.71
    POSITIVE LOGITS
     myriad
    1.91
     grandiose
    1.81
     horrid
    1.77
     a
    1.76
     strikingly
    1.73
    せっ
    1.72
     Brings
    1.70
     freakin
    1.70
     dilapidated
    1.70
    8
    1.69
    Activations Density 0.023%

    No Known Activations