© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 140900
    Prev
    Next
    INDEX
    Explanations

    security markings demonstration terminal underwear

    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
     instead
    0.52
    つ
    0.52
     eventually
    0.49
    ):(
    0.48
     lieu
    0.48
    eBay
    0.47
    シリーズ
    0.47
    ى
    0.47
    や
    0.47
     slabs
    0.46
    POSITIVE LOGITS
    öd
    0.54
    ressions
    0.53
    ancipation
    0.53
    INGS
    0.52
    pern
    0.50
    atios
    0.49
    ärt
    0.48
    gangenheit
    0.47
    ants
    0.47
    avi
    0.47
    Activations Density 0.000%

    No Known Activations