© 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. 17-GEMMASCOPE-2-RES-16K
    4. 10800
    Prev
    Next
    INDEX
    Explanations

    json object, array, or format

    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
    د
    2.97
     fleste
    2.38
    需要
    2.30
     Следу
    2.13
     caixa
    2.03
    ется
    2.01
    ेक्षित
    2.00
    setzung
    1.96
    دس
    1.95
    ів
    1.95
    POSITIVE LOGITS
    RationalValue
    3.11
    ो
    2.56
    m
    2.49
    er
    2.39
    い
    2.36
    ‍♀️
    2.34
    م
    2.29
    😂😂
    2.19
    ాన్ని
    2.17
    pire
    2.16
    Activations Density 0.041%

    No Known Activations