© 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. 49337
    Prev
    Next
    INDEX
    Explanations

    revealing or exposing

    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
    vesi
    -0.87
    inois
    -0.82
    cripted
    -0.79
     カットソー
    -0.79
    manas
    -0.78
    guten
    -0.77
    uxi
    -0.77
    ashir
    -0.77
    atoon
    -0.77
    urop
    -0.76
    POSITIVE LOGITS
     exposed
    3.63
    exposed
    3.09
    Exposed
    2.91
     bare
    2.81
     Exposed
    2.78
     exposing
    2.75
     expose
    2.70
     exposes
    2.52
     exposure
    2.34
     uncovered
    2.19
    Activations Density 0.057%

    No Known Activations