© 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. 12217
    Prev
    Next
    INDEX
    Explanations

    connecting together via

    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
     until
    -0.93
    jast
    -0.88
     to
    -0.84
     ended
    -0.81
     and
    -0.81
     changed
    -0.81
     usually
    -0.79
     probably
    -0.78
    arkas
    -0.78
     began
    -0.77
    POSITIVE LOGITS
    ⚖
    0.93
    อีก
    0.91
     '/':
    0.91
    Then
    0.90
     zwi
    0.89
     スカート
    0.85
     tissus
    0.84
    րան
    0.83
     organes
    0.83
     another
    0.82
    Activations Density 0.022%

    No Known Activations