© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 563
    Prev
    Next
    INDEX
    Explanations

    Isle of, Islanders, isles

    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
    渽
    -2.42
    揼
    -2.30
    暌
    -2.16
    ”
    -2.13
    獴
    -2.09
     hurting
    -2.05
    禤
    -2.03
    ing
    -2.02
    extAlignment
    -1.98
    鎹
    -1.97
    POSITIVE LOGITS
     But
    2.58
    $
    2.55
    ation
    2.33
    珦
    2.30
    ),
    2.27
    ")
    
    2.23
     französische
    2.23
     \&
    2.22
     offizielle
    2.20
    ,’
    2.19
    Activations Density 0.003%

    No Known Activations