© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66999
    Prev
    Next
    INDEX
    Explanations

    past tense verbs and outcomes

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

    This neuron detects terms signaling budget- and finance-related adjustments, such as revenues falling short, spending cuts, and other fiscal changes.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     دخترانه
    -2.06
    ׇ
    -1.98
    暧
    -1.83
     навіть
    -1.79
    Considering
    -1.66
    TestingModule
    -1.63
     even
    -1.63
    Although
    -1.61
    #__
    -1.60
     الشاشة
    -1.55
    POSITIVE LOGITS
     don
    1.94
    િક
    1.93
     doesn
    1.90
     время
    1.84
     principalmente
    1.71
     السياس
    1.70
    ంగా
    1.70
     help
    1.68
    やろ
    1.68
     fréquemment
    1.66
    Activations Density 0.866%

    No Known Activations