© 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. 10-GEMMASCOPE-RES-131K
    7. 58194
    Prev
    Next
    INDEX
    Explanations

    alone or exclusively

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    糴
    -1.63
    逦
    -1.60
     rappeler
    -1.58
     alberi
    -1.57
     a
    -1.54
    蛏
    -1.52
    桖
    -1.52
    Ƭ
    -1.51
    ⇹
    -1.49
    NESS
    -1.48
    POSITIVE LOGITS
    </h2>
    1.84
     may
    1.77
     will
    1.74
     cannot
    1.70
     makes
    1.70
     adequately
    1.68
     provide
    1.67
     first
    1.65
     receives
    1.60
     could
    1.59
    Activations Density 0.008%

    No Known Activations