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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130339
    Prev
    Next
    INDEX
    Explanations

    The neuron detects news‐style financial or corporate performance language (e.g. earnings reports, quarters, metrics, announcements).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    startup announcements and funding

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     गर्न
    -0.96
    当店
    -0.96
    ！？
    -0.96
     adequate
    -0.95
    令和
    -0.93
     paragraph
    -0.91
     Getränke
    -0.91
     разъ
    -0.91
     tidak
    -0.90
    您
    -0.90
    POSITIVE LOGITS
     représentent
    1.22
    jshint
    1.13
    瞥
    1.09
    unächst
    1.07
     usuários
    1.05
    böz
    1.05
    arquía
    1.05
     appartiennent
    1.04
    throwing
    1.04
     sinais
    1.02
    Activations Density 0.091%

    No Known Activations