© 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. 34-GEMMASCOPE-RES-131K
    7. 99680
    Prev
    Next
    INDEX
    Explanations

    what it is

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

    The neuron strongly activates on financial/investment contexts (e.g. discussions of saving, growing money, bitcoin, years to invest) and ignores unrelated 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
     learnt
    -1.02
     artistes
    -0.99
     artiste
    -0.96
     совершенно
    -0.93
    這麼
    -0.92
     کیلومتر
    -0.91
     quaisquer
    -0.90
     hitherto
    -0.89
     siyang
    -0.89
    Alright
    -0.89
    POSITIVE LOGITS
     someday
    0.83
     they
    0.83
    也都
    0.79
     also
    0.78
     including
    0.78
    jelasan
    0.77
     others
    0.75
    cely
    0.75
     those
    0.75
     humilde
    0.75
    Activations Density 0.059%

    No Known Activations