© 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. 108657
    Prev
    Next
    INDEX
    Explanations

    school failures and improvements

    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
    sana
    -1.08
     eventi
    -1.06
     húmedo
    -0.99
    bezpe
    -0.98
     byd
    -0.96
     Renal
    -0.95
    EEPROM
    -0.95
     错误
    -0.94
     ogran
    -0.94
    ußer
    -0.93
    POSITIVE LOGITS
     teachers
    1.74
     kids
    1.69
     children
    1.66
     teacher
    1.61
     schools
    1.34
     education
    1.34
     students
    1.34
     standards
    1.30
     accountability
    1.28
     educational
    1.22
    Activations Density 0.042%

    No Known Activations