© 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. 11398
    Prev
    Next
    INDEX
    Explanations

    code blocks or questions

    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
     intricacies
    -2.59
     where
    -2.59
     when
    -2.58
     that
    -2.58
     if
    -2.52
     creating
    -2.50
    籐
    -2.45
     which
    -2.44
     get
    -2.44
    錨
    -2.42
    POSITIVE LOGITS
     magnificent
    2.97
    H
    2.67
     captivating
    2.66
    ↵
    2.64
     monstrous
    2.64
    {
    2.61
    not
    2.59
     majestic
    2.55
    IN
    2.50
     specif
    2.48
    Activations Density 0.000%

    No Known Activations