© 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. 45720
    Prev
    Next
    INDEX
    Explanations

    everyone else

    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
    Negative Logits
     novin
    -1.77
     высокая
    -1.62
     jedna
    -1.55
     vesel
    -1.52
    慊
    -1.50
    Gnome
    -1.49
     reklama
    -1.48
    鞮
    -1.48
    gruppo
    -1.47
     kvalit
    -1.46
    POSITIVE LOGITS
     остальных
    2.05
    is
    1.98
    }
    1.94
    8
    1.91
    ina
    1.87
    4
    1.84
    The
    1.80
    7
    1.80
    as
    1.78
    3
    1.77
    Activations Density 0.013%

    No Known Activations