© 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. 48942
    Prev
    Next
    INDEX
    Explanations

    matric exams, financial instruments

    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
     GRADUATE
    -0.84
    Graduate
    -0.82
    毁灭
    -0.79
    doctoral
    -0.78
     Undergraduate
    -0.77
    蹒
    -0.75
     AUC
    -0.75
    JoinColumn
    -0.75
    ccini
    -0.74
    ക്ഷ
    -0.74
    POSITIVE LOGITS
     pupils
    0.94
     Grade
    0.88
     FET
    0.87
     teachers
    0.81
    FET
    0.80
     Term
    0.79
     teacher
    0.76
    明年
    0.76
    pupil
    0.75
     Year
    0.73
    Activations Density 0.005%

    No Known Activations