© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 69212
    Prev
    Next
    INDEX
    Explanations

    Federal

    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
    Not in Any Lists

    No Comments

    Negative Logits
    verre
    -1.31
     originalen
    -1.16
     gangen
    -1.15
     élevés
    -1.13
     kommunik
    -1.13
     bym
    -1.10
     jät
    -1.10
    ㎜
    -1.10
    '],
    -1.09
    stande
    -1.09
    POSITIVE LOGITS
    了不少
    0.94
    Regi
    0.93
     ceux
    0.90
     finalement
    0.90
     bastion
    0.90
    それに
    0.88
     EMER
    0.88
     футболка
    0.88
     apoyo
    0.85
     giebt
    0.85
    Activations Density 0.027%

    No Known Activations