© 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. 22-GEMMASCOPE-RES-131K
    7. 14180
    Prev
    Next
    INDEX
    Explanations

    programming keywords and constructs

    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
     viviendas
    -1.01
     another
    -0.99
     biografi
    -0.98
    比べ
    -0.92
     now
    -0.92
     herself
    -0.90
     belga
    -0.90
     confluence
    -0.90
     barna
    -0.89
    软件特色
    -0.88
    POSITIVE LOGITS
     fará
    1.17
     tecnologie
    1.09
     opzioni
    1.09
     costante
    1.09
     azioni
    1.04
     utford
    1.03
     opportunità
    1.02
     prestazioni
    1.01
    はコチラ
    0.98
    However
    0.98
    Activations Density 0.040%

    No Known Activations