© 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. 34-GEMMASCOPE-RES-131K
    7. 78869
    Prev
    Next
    INDEX
    Explanations

    modal dialogs and visibility

    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
    冥
    -0.84
    estrogen
    -0.80
    ㄑ
    -0.76
     Alphabet
    -0.73
    途
    -0.73
     Cheer
    -0.73
     bearbeitet
    -0.71
    格
    -0.71
     Workers
    -0.70
    Workers
    -0.70
    POSITIVE LOGITS
     visible
    1.32
    VISIBLE
    1.29
    visible
    1.17
     Visible
    1.06
    Visible
    1.06
     visibles
    1.05
     fileList
    0.84
    setVisible
    0.83
     visibility
    0.78
     invisible
    0.75
    Activations Density 0.009%

    No Known Activations