© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 108212
    Prev
    Next
    INDEX
    Explanations

    expensive

    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_31_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
    ਭ
    0.40
     श्रेय
    0.38
     Timing
    0.37
     Bore
    0.37
    タイミング
    0.36
     ಭ
    0.36
    தை
    0.36
     FutureWarning
    0.35
    壘
    0.35
    ☯
    0.35
    POSITIVE LOGITS
     expensive
    0.88
     pricey
    0.87
     costly
    0.83
     costs
    0.81
     premium
    0.73
     prices
    0.72
     महंगी
    0.71
     costos
    0.71
     Expensive
    0.70
     koszt
    0.68
    Activations Density 0.169%

    No Known Activations