© 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. 86736
    Prev
    Next
    INDEX
    Explanations

    financial bailouts and rescues

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

    This neuron detects numeric tokens, such as digits, years, dollar amounts, and other number-related expressions.

    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
    dukan
    -0.82
    sustaining
    -0.76
    Ꮮ
    -0.75
     sustaining
    -0.75
    சிய
    -0.71
    ]--;
    -0.71
     chanted
    -0.71
    シェフ
    -0.71
    Démographie
    -0.71
    Anlage
    -0.71
    POSITIVE LOGITS
     bailout
    1.95
     TAR
    1.55
     bail
    1.48
     rescue
    1.42
     Trou
    1.32
     Bail
    1.29
     Treasury
    1.18
    TAR
    1.18
    bail
    1.18
    Bail
    1.17
    Activations Density 0.025%

    No Known Activations