© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 11915
    Prev
    Next
    INDEX
    Explanations

    asking price

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

    The main thing this neuron does is detect numeric tokens (i.e. sequences of digits and monetary amounts) in the text.

    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
     時代
    -0.81
     опла
    -0.78
    aldo
    -0.77
     Beep
    -0.76
    Œ
    -0.75
     प्य
    -0.71
     urch
    -0.71
    fullWidth
    -0.69
     Caja
    -0.69
    esine
    -0.69
    POSITIVE LOGITS
     asking
    4.09
     Asking
    3.25
    Asking
    3.13
    asking
    3.09
     asks
    2.53
     ask
    2.39
     asked
    2.28
     Ask
    1.99
    ASK
    1.98
    ask
    1.90
    Activations Density 0.018%

    No Known Activations