© 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. 34-GEMMASCOPE-RES-131K
    7. 1855
    Prev
    Next
    INDEX
    Explanations

    sales targets or funding goals

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

    The neuron is looking for numeric expressions—digits, numbers, and related symbols (e.g. monetary amounts, percentages, counts).

    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
     hígado
    -0.95
     sauté
    -0.89
    țiune
    -0.86
    Took
    -0.86
    ⋁
    -0.84
     ude
    -0.82
    koper
    -0.81
    ISCH
    -0.81
    弊社
    -0.81
    いよいよ
    -0.81
    POSITIVE LOGITS
     target
    5.03
     targets
    4.72
     goal
    4.50
    target
    4.06
    目標
    4.00
    目标
    3.75
     goals
    3.73
     Targets
    3.64
     Target
    3.63
    Target
    3.55
    Activations Density 0.060%

    No Known Activations