© 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. 713
    Prev
    Next
    INDEX
    Explanations

    primitive long type in code

    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
    퐼
    -2.14
    鰱
    -2.06
    ༛
    -2.02
    鶿
    -2.02
    粜
    -2.00
     festgelegt
    -1.96
     gekennzeichnet
    -1.90
    ⌵
    -1.88
    蟶
    -1.87
     nastro
    -1.84
    POSITIVE LOGITS
     /
    2.27
    '
    2.25
     $
    1.97
    -
    1.90
    an
    1.70
     is
    1.64
     
    1.64
     "
    1.57
     at
    1.52
     In
    1.52
    Activations Density 0.005%

    No Known Activations