© 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. 41-GEMMASCOPE-2-RES-262K
    7. 33500
    Prev
    Next
    INDEX
    Explanations

    intelligent surveillance systems

    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_all/layer_41_width_262k_l0_big
    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
     depriving
    0.50
    ${\
    0.45
    ណ៍
    0.41
     slapping
    0.41
    电线路
    0.41
     inappropri
    0.40
    けん
    0.39
     repulsive
    0.38
     المعادله
    0.38
    蝼
    0.38
    POSITIVE LOGITS
     X
    0.51
     Y
    0.49
    X
    0.47
    Kok
    0.47
     Kok
    0.46
     kok
    0.45
     Target
    0.43
     Van
    0.42
    LT
    0.42
    Ma
    0.42
    Activations Density 0.000%

    No Known Activations