© 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. 676
    Prev
    Next
    INDEX
    Explanations

    database query results

    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
    ”,
    -2.56
    U
    -2.25
    F
    -2.23
     (“
    -2.19
     That
    -2.19
     هناك
    -2.14
    觏
    -2.13
    譬
    -2.02
    تیجه
    -2.00
    ,”
    -1.88
    POSITIVE LOGITS
                
    2.52
    甶
    2.34
    
    2.33
    ︕
    2.25
    苙
    2.25
    𐄁
    2.25
     utilizzo
    2.17
    GEBUR
    2.14
    ܆
    2.13
    ............
    2.11
    Activations Density 0.002%

    No Known Activations