© 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. 30231
    Prev
    Next
    INDEX
    Explanations

    licenses and version numbers

    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
     easy
    -0.77
    easy
    -0.76
     fence
    -0.73
     value
    -0.73
     friendship
    -0.71
    ဌ
    -0.69
     basic
    -0.69
     mujer
    -0.69
     znaczy
    -0.69
    塀
    -0.68
    POSITIVE LOGITS
     pimples
    0.79
    volent
    0.75
     Dian
    0.71
    currentItem
    0.70
     diligen
    0.69
    nummer
    0.68
     pter
    0.68
     Dik
    0.67
    czema
    0.65
     Mozilla
    0.65
    Activations Density 0.070%

    No Known Activations