© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 118719
    Prev
    Next
    INDEX
    Explanations

    attack vectors, atomic swaps, X Record, bloodborne

    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
     be
    0.57
    r
    0.56
     can
    0.49
    یس
    0.49
    </span>
    0.48
    m
    0.48
     안정
    0.48
     未来
    0.48
    up
    0.47
     会
    0.47
    POSITIVE LOGITS
    ല്‍
    0.53
    娛樂
    0.49
     nigris
    0.49
     carinatis
    0.49
    飲
    0.49
     rétrécies
    0.48
     groupings
    0.48
    дят
    0.46
     uniques
    0.45
     generalizations
    0.45
    Activations Density 0.000%

    No Known Activations