© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92513
    Prev
    Next
    INDEX
    Explanations

    fig. followed by numbers

    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
     even
    -0.90
     any
    -0.88
     all
    -0.86
     Even
    -0.84
     There
    -0.83
    Even
    -0.81
     every
    -0.80
     nổi
    -0.79
     commonly
    -0.79
     more
    -0.79
    POSITIVE LOGITS
     Fig
    1.91
    Fig
    1.91
     Figs
    1.66
    FIG
    1.37
    Figs
    1.26
     fig
    1.20
    fig
    1.20
     FIG
    1.13
    //////////////
    1.07
     vieill
    1.05
    Activations Density 0.005%

    No Known Activations