© 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. 25054
    Prev
    Next
    INDEX
    Explanations

    currency, PHP, Python, gold

    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
     Giochi
    -1.22
     turco
    -1.21
     Aeronau
    -1.19
     cristian
    -1.17
     Archite
    -1.17
     薬局
    -1.13
     Août
    -1.13
     poliester
    -1.10
     Stampa
    -1.09
     vasco
    -1.09
    POSITIVE LOGITS
     by
    1.34
     with
    1.30
     والذي
    1.23
     at
    1.21
     from
    1.08
     who
    1.06
     for
    1.00
    struttura
    1.00
     والتي
    0.93
     or
    0.92
    Activations Density 0.205%

    No Known Activations