© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 106923
    Prev
    Next
    INDEX
    Explanations

    assets and property descriptions

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

    The neuron fires on legal-or-financial terms naming or categorizing assets and property (e.g. loans, assignments, accounts receivable, inventory, mortgages, termination value).

    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
     okuyayım
    -0.81
    ANTED
    -0.77
    🥍
    -0.75
    ąc
    -0.74
     مراجع
    -0.72
    Новости
    -0.70
    VISUAL
    -0.69
    zzá
    -0.69
     variétés
    -0.69
    ampling
    -0.67
    POSITIVE LOGITS
     furniture
    1.74
     movable
    1.69
     equipment
    1.56
     machinery
    1.54
     stocks
    1.48
     buildings
    1.46
     vehicles
    1.45
     land
    1.38
     livestock
    1.33
     moveable
    1.31
    Activations Density 0.033%

    No Known Activations