© 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. 53-GEMMASCOPE-2-RES-262K
    7. 37581
    Prev
    Next
    INDEX
    Explanations

    crafting malicious prompts

    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_53_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
     big
    0.38
     Shao
    0.38
    rrrr
    0.38
     plan
    0.38
    "],[
    0.38
    shtml
    0.38
    ونکي
    0.38
     Pedal
    0.38
    ?!?!
    0.37
    tted
    0.37
    POSITIVE LOGITS
     vessel
    0.55
     vessels
    0.52
    Cloud
    0.51
     сосу
    0.47
     Cloud
    0.45
     cloud
    0.45
    云
    0.44
     Vessel
    0.44
     vess
    0.43
    容器
    0.40
    Activations Density 0.001%

    No Known Activations