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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68532
    Prev
    Next
    INDEX
    Explanations

    scenario or hypothetical situations

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

    The neuron detects discourse‐introducing “this” phrases followed by a colon—e.g. “Picture this scenario:” or “goes like this:”—which mark the start of an illustrative example.

    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
    พาะ
    -0.97
    cová
    -0.94
     главное
    -0.93
    繚
    -0.92
     Bakan
    -0.92
     filings
    -0.90
     also
    -0.90
     are
    -0.90
    нием
    -0.89
    íodo
    -0.89
    POSITIVE LOGITS
     scenario
    2.31
     scenarios
    1.73
    scenario
    1.68
    Scenario
    1.59
     Scenario
    1.52
     hypothetical
    1.39
    scenarios
    1.34
    ENARIO
    1.24
    よくある
    1.23
     Scenarios
    1.20
    Activations Density 0.063%

    No Known Activations