© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 148196
    Prev
    Next
    INDEX
    Explanations

    SQL Injection

    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
     Emerald
    0.81
     подру
    0.75
     laguna
    0.71
    execute
    0.69
    perf
    0.68
     Crow
    0.68
     Emory
    0.68
    벤
    0.67
     Sentence
    0.67
     Lark
    0.67
    POSITIVE LOGITS
     vorbere
    0.91
    嘬
    0.79
    ës
    0.76
     prepared
    0.75
    ရပ်
    0.71
    खुद
    0.70
     przygot
    0.69
     residences
    0.68
     ergeben
    0.67
    ظم
    0.67
    Activations Density 0.002%

    No Known Activations