© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 8971
    Prev
    Next
    INDEX
    Explanations

    roof inspections and repairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    ção
    2.86
    ка
    2.84
     propriétaire
    2.73
    ্লিষ্ট
    2.65
    ında
    2.62
    о
    2.58
     Faites
    2.55
    UTION
    2.55
    kości
    2.53
    erà
    2.52
    POSITIVE LOGITS
    ل
    3.35
    म
    3.33
    事情
    2.98
    ש
    2.93
    ેલા
    2.79
    𝘀
    2.77
    ات
    2.75
    wink
    2.74
    rocket
    2.72
    ed
    2.70
    Activations Density 0.020%

    No Known Activations