© 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. 77805
    Prev
    Next
    INDEX
    Explanations

    belie or betraying appearance

    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
    ﹚
    -0.76
    𝑍
    -0.73
     kontakta
    -0.72
     resection
    -0.71
    ABN
    -0.71
    bingo
    -0.70
    EXECUTIVE
    -0.69
    asztal
    -0.68
     получила
    -0.68
    ずつ
    -0.68
    POSITIVE LOGITS
     belie
    2.88
     hides
    1.77
     masks
    1.75
     betray
    1.68
     disgu
    1.66
     deceptive
    1.63
     betrayed
    1.63
     betrays
    1.60
     masking
    1.57
     concealing
    1.56
    Activations Density 0.042%

    No Known Activations