© 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. 47169
    Prev
    Next
    INDEX
    Explanations

    some kind of

    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
    Negative Logits
     quelques
    -1.41
    
    -1.24
    ⛤
    -1.17
    ckets
    -1.15
     septem
    -1.10
    蕺
    -1.09
    KKKK
    -1.05
    vereign
    -1.05
    𓁹
    -1.02
    ências
    -1.02
    POSITIVE LOGITS
     sort
    2.88
     kind
    2.75
     type
    1.70
     form
    1.63
    sort
    1.57
    ones
    1.55
    kind
    1.53
     rodzaj
    1.50
     version
    1.50
     mechanism
    1.45
    Activations Density 0.052%

    No Known Activations