© 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. 34-GEMMASCOPE-RES-131K
    7. 118953
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols immediately following punctuation

    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_34/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
     BufferedWriter
    -1.27
    ظه
    -1.20
     that
    -1.17
     нарушения
    -1.12
    ûr
    -1.05
     FileWriter
    -1.04
     centímetros
    -0.99
    Leírás
    -0.98
     when
    -0.97
    himself
    -0.97
    POSITIVE LOGITS
     กรัม
    1.03
     לעשות
    0.98
     tych
    0.96
    ême
    0.94
     verschillende
    0.92
     implor
    0.92
     acri
    0.91
     ridiculously
    0.90
     يوجد
    0.90
    na
    0.89
    Activations Density 0.004%

    No Known Activations