© 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. 741
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers and codes

    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
    '
    -2.05
    
    -1.96
     getNombre
    -1.89
    ikuti
    -1.88
    ','#
    -1.86
    สำหรับ
    -1.85
     Agrega
    -1.80
    ﹐
    -1.80
    蛏
    -1.78
     Temporada
    -1.77
    POSITIVE LOGITS
            
    2.33
    in
    2.28
    of
    2.05
     представ
    2.02
     \
    1.85
    からです
    1.84
    ()
    1.81
    i
    1.81
    上記
    1.81
     榜
    1.80
    Activations Density 0.012%

    No Known Activations