© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13378
    Prev
    Next
    INDEX
    Explanations

    noun followed by a noun/descriptor

    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
     ܐ
    -1.27
     regresa
    -1.20
     continúa
    -1.16
     నీ
    -1.15
    kawaii
    -1.15
     doba
    -1.15
    umid
    -1.15
    惬
    -1.09
    ternut
    -1.09
     cayó
    -1.09
    POSITIVE LOGITS
     of
    1.33
    元年
    1.05
    nościo
    1.00
    憲法
    0.97
     Figuren
    0.96
     Branchen
    0.95
     consentement
    0.94
    hi
    0.94
    +)/
    0.92
    tos
    0.91
    Activations Density 0.002%

    No Known Activations