© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 162899
    Prev
    Next
    INDEX
    Explanations

    price or cost perception

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

    expensive items and costs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Фі
    0.70
     FODC
    0.68
     Де
    0.64
     Бре
    0.63
     Кур
    0.62
     Несмотря
    0.61
     Віль
    0.60
    ゼ
    0.60
     Зе
    0.59
     Более
    0.59
    POSITIVE LOGITS
    v
    0.74
    im
    0.73
     cheap
    0.70
     dollars
    0.59
    ك
    0.59
     expensive
    0.59
     cheapest
    0.59
     barato
    0.59
     misconduct
    0.58
     prawo
    0.57
    Activations Density 0.047%

    No Known Activations