© 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. 34-GEMMASCOPE-RES-131K
    7. 81415
    Prev
    Next
    INDEX
    Explanations

    at stake or risk

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

    The neuron flags occurrences of “at stake” or similar phrasing that highlights what’s on the line or at risk.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     nødven
    -0.91
     کیلوم
    -0.81
    capai
    -0.79
     miljø
    -0.78
     nemá
    -0.75
    нется
    -0.75
     gewel
    -0.75
    ercicio
    -0.74
    թ
    -0.73
    rael
    -0.73
    POSITIVE LOGITS
     stake
    3.47
     stakes
    3.03
    stakes
    2.23
    stake
    2.23
     at
    2.16
     Stake
    2.02
     Stakes
    1.99
     staked
    1.85
    Stake
    1.63
     riding
    1.61
    Activations Density 0.034%

    No Known Activations