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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11474
    Prev
    Next
    INDEX
    Explanations

    articles and possessives

    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
     voren
    -1.26
     impecable
    -1.26
     després
    -1.25
     accesible
    -1.22
    
    -1.21
    "../
    -1.20
    vieux
    -1.20
     @"/
    -1.19
     bestellen
    -1.17
     imprimer
    -1.17
    POSITIVE LOGITS
     several
    1.63
     a
    1.62
     an
    1.61
     very
    1.44
     three
    1.38
     some
    1.34
     fairly
    1.33
     numerous
    1.32
     Would
    1.28
     horribly
    1.28
    Activations Density 0.030%

    No Known Activations