© 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. 22-GEMMASCOPE-RES-131K
    4. 11469
    Prev
    Next
    INDEX
    Explanations

    conjunctions and contrasting clauses

    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
     in
    -0.86
    caucasian
    -0.83
    ึ้น
    -0.82
     this
    -0.81
     镇
    -0.78
    Doing
    -0.73
     Denial
    -0.73
     within
    -0.73
    馒头
    -0.73
    orap
    -0.72
    POSITIVE LOGITS
    Regarding
    0.95
     begge
    0.93
     Regarding
    0.93
     concernant
    0.91
     ส่วน
    0.90
    については
    0.89
     regarding
    0.88
    latter
    0.87
     Beide
    0.87
    至於
    0.86
    Activations Density 0.067%

    No Known Activations