© 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. 22-GEMMASCOPE-RES-131K
    4. 40083
    Prev
    Next
    INDEX
    Explanations

    financial market sentiment

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

    The neuron primarily detects finance- and market-related terms.

    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
     juta
    -1.06
     充電
    -1.05
    ⋮
    -1.05
    unteers
    -0.98
     saisi
    -0.97
     miele
    -0.96
     use
    -0.95
    衣裙
    -0.93
     onPostExecute
    -0.93
    uestos
    -0.92
    POSITIVE LOGITS
     investors
    1.41
    ּוֹ
    1.37
    ַּ
    1.30
    ִּ
    1.19
    וּ
    1.08
    れている
    1.06
     investor
    1.06
    tojas
    1.04
     markets
    1.04
     mesto
    1.03
    Activations Density 0.012%

    No Known Activations