© 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. 10-GEMMASCOPE-RES-131K
    7. 13881
    Prev
    Next
    INDEX
    Explanations

    deceit, deception, deceive

    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
    Not in Any Lists

    No Comments

    Negative Logits
    N
    -2.67
    os
    -2.56
    洐
    -2.53
    .”
    -2.47
    .《
    -2.36
     leaſt
    -2.25
    身旁
    -2.20
    ”（
    -2.19
    不是很
    -2.16
    靣
    -2.16
    POSITIVE LOGITS
    {
    2.98
    '
    2.86
    it
    2.39
    that
    2.38
    ले
    2.14
     anderer
    2.14
     deceive
    2.13
     but
    2.09
     musíte
    2.09
     "
    2.06
    Activations Density 0.005%

    No Known Activations