© 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. 16-GEMMASCOPE-2-RES-262K
    7. 41428
    Prev
    Next
    INDEX
    Explanations

    ideas taking root

    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_16_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
     لوبې
    0.66
    с
    0.62
     он
    0.61
     ہندوستان
    0.60
    ওয়ে
    0.59
    endish
    0.57
    aparikkh
    0.57
     спів
    0.56
     تباہ
    0.56
    screenWidth
    0.55
    POSITIVE LOGITS
    ↵
    0.58
     Who
    0.57
    1
    0.54
     Janice
    0.54
     Paris
    0.52
     Earth
    0.51
     Empowerment
    0.51
     Seja
    0.50
     Market
    0.50
    b
    0.50
    Activations Density 0.000%

    No Known Activations