© 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. 10-GEMMASCOPE-RES-131K
    7. 15726
    Prev
    Next
    INDEX
    Explanations

    deception, lies, honesty

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     '
    -1.45
    ☑️
    -1.38
    ビジネス
    -1.38
     poule
    -1.30
    𓐍
    -1.30
    portug
    -1.27
    THEW
    -1.26
    쨌
    -1.25
    fokus
    -1.24
    Proteins
    -1.23
    POSITIVE LOGITS
     about
    1.77
    but
    1.40
     which
    1.37
     including
    1.34
     and
    1.34
     ,‬
    1.33
    瞞
    1.24
     שה
    1.21
     semplice
    1.21
     you
    1.20
    Activations Density 0.033%

    No Known Activations