© 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. 10-GEMMASCOPE-RES-131K
    7. 72011
    Prev
    Next
    INDEX
    Explanations

    completed acquisition

    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_10/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
     also
    -1.91
     tiež
    -1.35
     επίσης
    -1.32
     enmar
    -1.30
     Sollte
    -1.30
     extremadamente
    -1.26
     Vielleicht
    -1.25
     también
    -1.23
     antiguas
    -1.22
     भी
    -1.21
    POSITIVE LOGITS
     compared
    1.26
     completed
    1.21
    paedia
    1.20
    “)
    1.19
     tempore
    1.18
    UMMY
    1.16
    Comparer
    1.15
     bebes
    1.14
     bruto
    1.14
     concludes
    1.14
    Activations Density 0.067%

    No Known Activations