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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 25889
    Prev
    Next
    INDEX
    Explanations

    figures, plots, images

    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_34/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
    }[!
    -0.90
    That
    -0.86
     Some
    -0.84
    There
    -0.83
     for
    -0.81
     or
    -0.80
     What
    -0.79
     Live
    -0.78
    zA
    -0.76
     吗
    -0.74
    POSITIVE LOGITS
     figures
    1.25
     figure
    1.18
     plots
    1.16
    fig
    1.10
     figs
    1.07
     그림
    1.05
     eps
    1.04
     новую
    1.04
    eps
    1.03
     новое
    1.02
    Activations Density 0.027%

    No Known Activations