© 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. 17-GEMMASCOPE-2-RES-16K
    7. 15996
    Prev
    Next
    INDEX
    Explanations

    sub- categories / sub- topics

    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_17_width_16k_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
     Certainly
    1.67
     stup
    1.61
     hungry
    1.50
     certainly
    1.44
    ুর
    1.42
    ດ
    1.37
    to
    1.36
     selanjutnya
    1.36
    शेष
    1.34
     diketahui
    1.30
    POSITIVE LOGITS
    ेक्षा
    1.81
    erp
    1.78
    cribes
    1.70
    cultures
    1.63
    mitting
    1.57
    er
    1.57
    topics
    1.56
    ेक्षित
    1.55
    𝑠
    1.54
    ordinating
    1.53
    Activations Density 0.097%

    No Known Activations