© 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. 64747
    Prev
    Next
    INDEX
    Explanations

    reveal or disclose information

    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
    模样
    -0.81
    ۖ
    -0.75
     Kinetics
    -0.75
    浬
    -0.71
     kli
    -0.70
     Pape
    -0.70
    缪
    -0.70
    HttpStatusCode
    -0.69
     Interpolation
    -0.69
    콧
    -0.68
    POSITIVE LOGITS
     revelation
    1.30
     reveal
    1.20
     disclose
    1.03
     révé
    1.02
     reveals
    0.99
     revelations
    0.99
     clues
    0.98
     Reveal
    0.96
    reveal
    0.95
     revealed
    0.94
    Activations Density 0.008%

    No Known Activations