© 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. 30111
    Prev
    Next
    INDEX
    Explanations

    buying new things like homes

    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
     valide
    -0.92
     gegeben
    -0.90
     verstärkt
    -0.89
    usk
    -0.88
     ゼ
    -0.87
    ƌ
    -0.79
    letterSpacing
    -0.78
     startling
    -0.77
     favoriser
    -0.77
     craindre
    -0.76
    POSITIVE LOGITS
     dream
    1.42
    dream
    1.16
     new
    1.15
     perfect
    0.96
    夢
    0.89
     place
    0.86
     DREAM
    0.84
    urants
    0.84
     которы
    0.84
     permanent
    0.83
    Activations Density 0.037%

    No Known Activations