© 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. 78548
    Prev
    Next
    INDEX
    Explanations

    free zone, Lakes Towers, Q:, Agricultural research

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

    numbers and numerical data in documents, especially dates, prices, and quantities.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron fires on terms associated with formal trading and storage permissions—especially license verbs and crypto/commodity trading vocabulary.

    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
     Vehicle
    -0.73
     Ellen
    -0.72
     Elles
    -0.70
     Clifton
    -0.68
    alleria
    -0.68
     má
    -0.67
     Koh
    -0.67
    sams
    -0.66
     Nan
    -0.66
    бла
    -0.66
    POSITIVE LOGITS
    箓
    0.81
    uß
    0.81
     вікі
    0.77
    न्छ
    0.77
     wept
    0.77
    ᑭ
    0.77
     hivyo
    0.74
     tentunya
    0.74
    Mål
    0.73
    watches
    0.73
    Activations Density 0.013%

    No Known Activations