© 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. 16594
    Prev
    Next
    INDEX
    Explanations

    role and purpose

    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
    Hanya
    -1.30
    งิน
    -1.21
     vulné
    -1.17
     CYTHON
    -1.16
    ڧ
    -1.15
    kunjung
    -1.14
    monial
    -1.13
     salonu
    -1.12
    ſure
    -1.10
    ండ
    -1.09
    POSITIVE LOGITS
     respon
    1.60
     duties
    1.39
    ↵
    1.38
     job
    1.36
     tasks
    1.34
     task
    1.27
    —
    1.26
     work
    1.25
    --
    1.21
    –
    1.17
    Activations Density 0.023%

    No Known Activations