© 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. 118638
    Prev
    Next
    INDEX
    Explanations

    marking and grammar

    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
    żdy
    -0.85
     muffler
    -0.83
     migli
    -0.82
    さっき
    -0.82
    פון
    -0.81
     verschillen
    -0.78
     juft
    -0.77
     chargés
    -0.76
    ייס
    -0.75
     unchanging
    -0.75
    POSITIVE LOGITS
     marking
    1.13
     marker
    1.13
     markers
    0.98
    marking
    0.96
     marked
    0.94
     markings
    0.93
    Marking
    0.92
     marks
    0.90
    marked
    0.90
     unmarked
    0.87
    Activations Density 0.048%

    No Known Activations