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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 16259
    Prev
    Next
    INDEX
    Explanations

    leet speak substitutions

    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_17_width_16k_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
     T
    0.82
    О
    0.80
     t
    0.76
     C
    0.74
     Т
    0.73
     In
    0.72
     n
    0.72
     P
    0.72
     m
    0.71
     Co
    0.71
    POSITIVE LOGITS
    睃
    0.92
    katore
    0.92
    ătă
    0.91
     Diarsipkan
    0.87
    çou
    0.86
    鼕
    0.86
    <unused2221>
    0.85
    𒅀
    0.85
    🇫
    0.83
    ocurrency
    0.83
    Activations Density 0.001%

    No Known Activations