© 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. 22-GEMMASCOPE-2-RES-262K
    4. 18887
    Prev
    Next
    INDEX
    Explanations

    working memory, remains largely

    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_22_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
    nya
    0.83
     Emm
    0.80
     Wen
    0.79
    <0x80>
    0.77
    Ÿ
    0.76
    Ź
    0.74
     propylene
    0.73
     Touching
    0.72
    Touching
    0.72
    arr
    0.72
    POSITIVE LOGITS
    രിച്ചു
    0.92
    ország
    0.85
     leth
    0.80
    壅
    0.76
     মুক্তি
    0.76
    istic
    0.75
     ው
    0.74
    polished
    0.74
    моби
    0.73
     مصرف
    0.72
    Activations Density 0.000%

    No Known Activations