© 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. 22519
    Prev
    Next
    INDEX
    Explanations

    found in LICENSE file

    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
     morfo
    -1.55
     faciliter
    -1.51
     geografia
    -1.48
     bascul
    -1.48
     postura
    -1.46
     autonomia
    -1.45
    隂
    -1.45
     sinais
    -1.43
     atmosfera
    -1.39
     comunica
    -1.39
    POSITIVE LOGITS
     that
    1.80
     Those
    1.50
     Other
    1.50
     is
    1.49
    ví
    1.42
     These
    1.40
    Beskrivning
    1.39
     Another
    1.38
    命的
    1.37
     Things
    1.36
    Activations Density 0.008%

    No Known Activations