© 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. 47364
    Prev
    Next
    INDEX
    Explanations

    scientific calculation and code snippets

    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
     shrubs
    -0.74
    btnBack
    -0.73
    éro
    -0.71
     suya
    -0.69
     Taiwanese
    -0.67
    ipfel
    -0.65
     Cisco
    -0.65
     میشه
    -0.64
     רבה
    -0.64
     pigment
    -0.63
    POSITIVE LOGITS
     Kohn
    0.90
     fft
    0.88
     FFT
    0.88
     muffin
    0.83
    mtrl
    0.83
     projectors
    0.79
    iamo
    0.76
    🕣
    0.75
    تك
    0.75
     Weiterbildung
    0.73
    Activations Density 0.041%

    No Known Activations