© 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-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 14574
    Prev
    Next
    INDEX
    Explanations

    obtaining or experiencing something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_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
    an
    0.50
    ang
    0.46
    going
    0.45
    i
    0.45
    aking
    0.43
    ie
    0.41
    ig
    0.40
    assment
    0.39
    pering
    0.38
    nings
    0.38
    POSITIVE LOGITS
    د
    0.73
    д
    0.70
    人的
    0.53
    \
    0.52
     proizvod
    0.48
    cit
    0.48
     lindo
    0.47
    نت
    0.47
    ä
    0.47
     naudoj
    0.46
    Activations Density 0.105%

    No Known Activations