© 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. 10-GEMMASCOPE-RES-131K
    7. 110905
    Prev
    Next
    INDEX
    Explanations

    is or includes individuals

    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_10/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
     originalen
    -1.94
    ㈬
    -1.80
    acterísticas
    -1.73
     traditionelle
    -1.70
    ၜ
    -1.70
     notwendigen
    -1.67
    瘓
    -1.66
     praktische
    -1.63
     différentes
    -1.63
     vielen
    -1.59
    POSITIVE LOGITS
     who
    2.41
     those
    2.02
     people
    1.94
     by
    1.92
     members
    1.83
     young
    1.80
     bernama
    1.80
     you
    1.80
     him
    1.74
     individuals
    1.64
    Activations Density 0.082%

    No Known Activations