© 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. 577
    Prev
    Next
    INDEX
    Explanations

    degree of order

    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
    鬭
    -2.48
     volando
    -2.36
    
    -2.34
    詎
    -2.33
    迨
    -2.25
    
    -2.19
     parachoque
    -2.17
     vnt
    -2.16
    gucig
    -2.14
     itſelf
    -2.13
    POSITIVE LOGITS
    6
    2.42
    <em>
    2.38
     innym
    2.22
     \
    2.22
     />
    2.19
    4
    2.19
    ”
    2.16
    »
    2.13
    ,'
    2.09
    urtstag
    2.09
    Activations Density 0.014%

    No Known Activations