© 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
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 9085
    Prev
    Next
    INDEX
    Explanations

    common and important descriptions

    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
    н
    2.41
    一个
    2.20
    ה
    2.14
    a
    1.94
    其他
    1.79
    च
    1.78
    ট
    1.74
    一个新的
    1.71
    ه
    1.69
     kalt
    1.68
    POSITIVE LOGITS
    کیل
    1.68
    кона
    1.62
    گان
    1.57
    camb
    1.56
    בים
    1.56
    wiście
    1.53
    риди
    1.53
    RelativeLayout
    1.52
    ου
    1.51
     जहां
    1.50
    Activations Density 0.093%

    No Known Activations