© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 149857
    Prev
    Next
    INDEX
    Explanations

    cross site scripting (xss)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
    緩
    0.82
     근무
    0.81
    ম্ভীর
    0.80
    踽
    0.80
     incarcerated
    0.80
    再
    0.79
     belirtti
    0.79
     detention
    0.77
     kojima
    0.77
    俘
    0.77
    POSITIVE LOGITS
    rs
    0.86
     legg
    0.80
    est
    0.77
     Close
    0.76
    assemble
    0.76
    leg
    0.75
     located
    0.74
    னால
    0.74
    넣
    0.73
     Name
    0.73
    Activations Density 0.001%

    No Known Activations