© 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. 3344
    Prev
    Next
    INDEX
    Explanations

    years and punctuation

    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
    Not in Any Lists

    No Comments

    Negative Logits
     July
    -0.87
     octobre
    -0.85
     sını
    -0.82
     components
    -0.79
     Tän
    -0.77
     increasingly
    -0.77
     on
    -0.75
    办事
    -0.74
    DoesNotExist
    -0.73
     Jär
    -0.73
    POSITIVE LOGITS
    COMMUNIC
    1.07
     respiración
    0.93
    ;">
    0.90
    erein
    0.89
     fatale
    0.88
     eier
    0.87
     stille
    0.85
    vide
    0.84
     nabo
    0.83
     szob
    0.83
    Activations Density 0.012%

    No Known Activations