© 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. 110656
    Prev
    Next
    INDEX
    Explanations

    quotation marks or enclosing characters

    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
     new
    -1.11
     their
    -1.07
    感じで
    -0.99
    github
    -0.96
    ﻮ
    -0.94
    ಯ
    -0.91
     get
    -0.90
    บุ
    -0.88
     sveta
    -0.88
     if
    -0.86
    POSITIVE LOGITS
     “
    1.73
     "
    1.45
     «
    1.13
    ‟
    1.04
     „
    1.00
    …)
    0.98
    owań
    0.93
    MQTT
    0.93
     ”
    0.92
     intermin
    0.91
    Activations Density 0.023%

    No Known Activations