© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70969
    Prev
    Next
    INDEX
    Explanations

    states of being, progress, or events

    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
    Not in Any Lists

    No Comments

    Negative Logits
    –
    -2.03
    .
    -1.85
    -
    -1.82
     .
    -1.69
    {
    -1.69
     venerable
    -1.66
    :
    -1.57
    ’
    -1.56
     devout
    -1.55
    やってる
    -1.53
    POSITIVE LOGITS
     for
    2.05
     alberi
    1.84
    licante
    1.84
    gencias
    1.83
    istán
    1.72
     användas
    1.71
     adanya
    1.70
     keluarganya
    1.70
     pernikahan
    1.68
     militare
    1.68
    Activations Density 0.078%

    No Known Activations