© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15365
    Prev
    Next
    INDEX
    Explanations

    file paths and directory names

    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
    ,
    -1.55
     грамм
    -1.52
    -
    -1.50
     PRODUCTO
    -1.49
    and
    -1.44
    0
    -1.44
     grises
    -1.42
    _
    -1.42
     rendus
    -1.41
    e
    -1.37
    POSITIVE LOGITS
     presently
    1.66
     between
    1.64
     hopes
    1.58
     collegamento
    1.55
     previously
    1.55
     distribuzione
    1.55
     particolar
    1.55
     protože
    1.54
    occasione
    1.47
     veicolo
    1.45
    Activations Density 0.028%

    No Known Activations