© 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. 3398
    Prev
    Next
    INDEX
    Explanations

    pro se

    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
     subroutine
    -0.77
    ویری
    -0.70
    PROBE
    -0.69
    mountable
    -0.68
     Provider
    -0.68
     вку
    -0.68
     カフェ
    -0.68
    可在
    -0.68
     authoritative
    -0.68
     عال
    -0.67
    POSITIVE LOGITS
     represented
    1.79
    representing
    1.63
    represented
    1.63
     representing
    1.61
     self
    1.61
    Represent
    1.59
     pro
    1.48
     Representing
    1.48
     represent
    1.45
     representation
    1.45
    Activations Density 0.054%

    No Known Activations