© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 205020
    Prev
    Next
    INDEX
    Explanations

    market expansion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    胙
    0.43
    uchs
    0.41
    ját
    0.40
    ⌊
    0.39
    vať
    0.38
    gcj
    0.38
    စဉ်
    0.38
    溺
    0.38
    VAT
    0.37
    vat
    0.37
    POSITIVE LOGITS
     market
    0.57
     Market
    0.52
    market
    0.46
     MARKET
    0.45
     mercado
    0.45
     Wood
    0.44
     시장
    0.44
     markets
    0.42
     marché
    0.42
     mercados
    0.41
    Activations Density 0.002%

    No Known Activations