© 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. 22-GEMMASCOPE-RES-131K
    7. 12192
    Prev
    Next
    INDEX
    Explanations

    customer context and attributes

    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_22/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
     also
    -2.77
    你也
    -2.58
     fosters
    -2.41
     they
    -2.25
    就像
    -2.23
     You
    -2.22
    女孩子
    -2.22
     неболь
    -2.19
    ,"
    -2.17
     Addressing
    -2.17
    POSITIVE LOGITS
    ⩩
    2.70
    狆
    2.55
    
    2.41
    ୌ
    2.36
    
    2.34
    इटम
    2.33
    their
    2.33
    ⭏
    2.31
    ᎒
    2.31
    ᭝
    2.28
    Activations Density 0.016%

    No Known Activations