© 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. 12296
    Prev
    Next
    INDEX
    Explanations

    sports events and categories

    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
     negligible
    -0.98
    If
    -0.91
    reak
    -0.90
     stava
    -0.90
    It
    -0.89
    Decry
    -0.88
    formatted
    -0.87
    RE
    -0.85
    配
    -0.84
     圣诞
    -0.84
    POSITIVE LOGITS
     categories
    1.30
     such
    1.23
     ayudan
    1.13
    mantec
    1.09
    fastjson
    1.07
    乩
    1.05
     championnat
    1.03
    laken
    1.03
    TestingModule
    1.01
     betroffen
    1.01
    Activations Density 0.066%

    No Known Activations