© 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. 94207
    Prev
    Next
    INDEX
    Explanations

    menu items or sections

    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
    geſ
    -1.02
    odeon
    -1.02
    YSTAL
    -0.94
     genügend
    -0.93
    khana
    -0.92
    bites
    -0.91
     ένα
    -0.90
    ༔
    -0.90
     murmur
    -0.90
     wichtigen
    -0.89
    POSITIVE LOGITS
    item
    1.30
     item
    1.26
     items
    1.22
    项
    0.99
    kaart
    0.96
    Men
    0.94
     vivía
    0.93
     choice
    0.92
     system
    0.91
     Мен
    0.90
    Activations Density 0.018%

    No Known Activations