© 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. 107190
    Prev
    Next
    INDEX
    Explanations

    fear, reverence, irreverence

    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
    kari
    -0.80
     DB
    -0.78
    西藏
    -0.76
    ニラ
    -0.75
    peek
    -0.73
     Savior
    -0.69
    alous
    -0.69
     урока
    -0.69
    Hog
    -0.69
    Style
    -0.68
    POSITIVE LOGITS
     fear
    2.33
    fear
    2.05
     Fear
    1.96
    Fear
    1.92
     fearing
    1.88
     FEAR
    1.62
     piety
    1.52
     feared
    1.51
     fears
    1.49
     reverence
    1.23
    Activations Density 0.015%

    No Known Activations