© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32036
    Prev
    Next
    INDEX
    Explanations

    discipline and disciplinary proceedings

    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
     Between
    -1.07
     Careful
    -1.03
     unending
    -0.92
    難易
    -0.91
     tremendous
    -0.88
     produite
    -0.86
    前面的
    -0.85
     Quality
    -0.85
     Literally
    -0.84
     complexo
    -0.84
    POSITIVE LOGITS
     discipline
    2.06
    discipline
    1.92
     disciplinary
    1.91
     Discipline
    1.88
     discipl
    1.77
     disciplines
    1.75
     Discipl
    1.63
     DISCIP
    1.59
    discipl
    1.52
    disciplinary
    1.52
    Activations Density 0.022%

    No Known Activations