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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26952
    Prev
    Next
    INDEX
    Explanations

    image dimensions and sizes

    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
     dabar
    -1.09
    Ħ
    -1.03
    Generally
    -1.03
     kän
    -0.97
    czema
    -0.96
     apsau
    -0.96
     Generally
    -0.95
    Sinopse
    -0.95
    sobí
    -0.95
     of
    -0.94
    POSITIVE LOGITS
     cuna
    1.06
     limpia
    1.01
     rappresent
    1.01
     its
    1.00
     dokter
    0.97
     серия
    0.94
     renuncia
    0.93
    particularly
    0.91
     ו
    0.90
     usado
    0.90
    Activations Density 0.023%

    No Known Activations