© 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. 702
    Prev
    Next
    INDEX
    Explanations

    Wilmington or Wanderers

    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
    ㍑
    -2.69
    تیجه
    -2.59
     Главная
    -2.42
     kalt
    -2.39
    鉿
    -2.38
     ‘‘
    -2.34
    Ꮞ
    -2.34
    赑
    -2.33
     stille
    -2.30
    ㌘
    -2.30
    POSITIVE LOGITS
    
    2.95
     として
    2.44
    }=\
    2.33
     and
    2.31
    ])
    2.28
     he
    2.25
    呖
    2.22
    UIControlState
    2.20
    祤
    2.13
    \%)
    2.06
    Activations Density 0.002%

    No Known Activations