© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25120
    Prev
    Next
    INDEX
    Explanations

    deliberate and hidden actions

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ressions
    -0.89
    dillas
    -0.89
     albic
    -0.84
    strando
    -0.83
    ybės
    -0.82
    onicus
    -0.81
     scraper
    -0.81
     aluminio
    -0.81
     idolatry
    -0.81
    ahua
    -0.80
    POSITIVE LOGITS
     secret
    1.09
     conspiracy
    0.95
     intentionally
    0.94
     deliberately
    0.93
     intentional
    0.90
     deliberate
    0.89
    seeded
    0.88
     hidden
    0.88
    故意
    0.88
     behind
    0.87
    Activations Density 0.064%

    No Known Activations