© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 589
    Prev
    Next
    INDEX
    Explanations

    code method calls and proper nouns

    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
    s
    -4.06
    h
    -3.44
    j
    -2.80
    e
    -2.36
    ta
    -2.36
    ons
    -2.34
    n
    -2.31
    a
    -2.30
    f
    -2.23
    x
    -2.23
    POSITIVE LOGITS
    骜
    2.69
     Artículos
    2.30
     façade
    2.22
     Fotografía
    2.06
     nieuwe
    2.02
    
    2.02
     herido
    2.00
    dientemente
    1.97
    
    1.97
     condenado
    1.96
    Activations Density 0.000%

    No Known Activations