© 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. 24968
    Prev
    Next
    INDEX
    Explanations

    HTTP status and success codes

    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
    zione
    -1.49
     anderen
    -1.43
    !"
    -1.41
     with
    -1.40
     additional
    -1.34
     dostępne
    -1.33
     in
    -1.27
     жидко
    -1.27
    "
    -1.26
    "!
    -1.25
    POSITIVE LOGITS
     womit
    1.49
    姈
    1.30
    鸝
    1.25
     ?";
    1.23
     женщины
    1.21
     cependant
    1.21
     местных
    1.20
    ]
    1.20
    茈
    1.19
     jis
    1.18
    Activations Density 0.000%

    No Known Activations