© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38249
    Prev
    Next
    INDEX
    Explanations

    current state and status

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron primarily activates on occurrences of the word “state” (and closely related terms like snapshot or recorded state).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     pasirink
    -1.05
     dentro
    -1.01
     någon
    -1.00
    mous
    -0.98
    FIRST
    -0.97
    lovak
    -0.96
    shortest
    -0.95
    chaik
    -0.95
    EntryPoint
    -0.94
    AN
    -0.93
    POSITIVE LOGITS
     changes
    1.71
     current
    1.48
     state
    1.45
     situation
    1.39
     status
    1.39
     configuration
    1.34
     keadaan
    1.32
     changed
    1.30
     situations
    1.30
     information
    1.27
    Activations Density 0.036%

    No Known Activations