© 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. 22-GEMMASCOPE-RES-131K
    7. 26649
    Prev
    Next
    INDEX
    Explanations

    deceived or misled

    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
    Not in Any Lists

    No Comments

    Negative Logits
    决心
    -1.00
    ヒント
    -0.89
     äls
    -0.88
    فاق
    -0.86
    その時
    -0.84
    Aula
    -0.84
    證明
    -0.84
    逆に
    -0.83
     جات
    -0.83
    ाप
    -0.83
    POSITIVE LOGITS
     naïve
    1.09
     naive
    1.02
     deceived
    0.98
    Zeneca
    0.94
    ℣
    0.93
    quê
    0.91
    blind
    0.91
    σουν
    0.90
     misled
    0.90
     unsuspecting
    0.89
    Activations Density 0.050%

    No Known Activations