© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2835
    Prev
    Next
    INDEX
    Explanations

    technical versions and algorithms

    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
     and
    -2.06
     this
    -1.80
     it
    -1.70
     an
    -1.66
     providing
    -1.65
     facilitating
    -1.61
     a
    -1.58
     bringing
    -1.58
     as
    -1.57
    strator
    -1.57
    POSITIVE LOGITS
     REALLY
    1.80
     wondrous
    1.72
     AMAZING
    1.72
     masterful
    1.59
     mediocre
    1.58
     strikingly
    1.58
     unbelievably
    1.57
     juſt
    1.57
     tumultuous
    1.57
    mainly
    1.57
    Activations Density 0.007%

    No Known Activations