© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64417
    Prev
    Next
    INDEX
    Explanations

    options and conclusions

    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
     włosów
    -0.83
    Selective
    -0.82
     Selective
    -0.81
    dı
    -0.73
     selective
    -0.73
     високо
    -0.72
    VARIABLES
    -0.72
    textfield
    -0.71
    %!
    -0.70
    setResult
    -0.69
    POSITIVE LOGITS
    Hence
    1.45
    Therefore
    1.34
     hence
    1.29
    hence
    1.27
     Hence
    1.23
     thus
    1.16
    Thus
    1.15
     Therefore
    1.07
    option
    1.05
     option
    1.04
    Activations Density 0.007%

    No Known Activations