© 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. 22-GEMMASCOPE-RES-131K
    7. 25094
    Prev
    Next
    INDEX
    Explanations

    reason, time, source, cause

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     fald
    -1.21
     vencedor
    -1.16
     jule
    -1.13
    "+
    -1.13
    Ils
    -1.12
     palio
    -1.11
     etui
    -1.09
     Polonia
    -1.09
     lada
    -1.08
     xvii
    -1.06
    POSITIVE LOGITS
     because
    1.38
     after
    1.27
     assistir
    1.26
     seguía
    1.25
     jednod
    1.23
     herido
    1.23
     Beschäf
    1.23
     благодаря
    1.20
     when
    1.20
     semplicemente
    1.19
    Activations Density 0.051%

    No Known Activations