© 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. 60713
    Prev
    Next
    INDEX
    Explanations

    linear equations and coefficients

    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
     informática
    -0.81
    ക്ക്
    -0.75
    雉
    -0.74
     wskaz
    -0.73
    Begin
    -0.73
     demasiado
    -0.71
    eably
    -0.68
    ducation
    -0.68
    Ecotoxicity
    -0.68
    Benz
    -0.68
    POSITIVE LOGITS
     bias
    2.28
    bias
    1.90
     biases
    1.88
     Bias
    1.75
    Bias
    1.69
     intercept
    1.59
    biases
    1.50
    intercept
    1.50
     Offset
    1.45
    BIAS
    1.45
    Activations Density 0.058%

    No Known Activations