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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 109127
    Prev
    Next
    INDEX
    Explanations

    low and middle income

    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
    hitva
    0.41
    별
    0.38
    panic
    0.36
    спеди
    0.35
     अंगों
    0.35
     धन
    0.35
    Panic
    0.35
     anxiety
    0.34
    धन
    0.34
    িবার
    0.34
    POSITIVE LOGITS
     low
    0.84
     fixed
    0.72
     middle
    0.71
    low
    0.67
    低
    0.66
     düşük
    0.61
    middle
    0.60
    固定
    0.60
     LOW
    0.59
    fixed
    0.58
    Activations Density 0.013%

    No Known Activations