© 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
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 14153
    Prev
    Next
    INDEX
    Explanations

    ai, ei, and similar vowel sounds

    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_22_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
    ীয়
    1.16
    ียม
    1.15
    ೕ
    1.14
     cDNA
    1.13
    ać
    1.07
    ीय
    1.07
     intrusion
    1.05
    اؤ
    1.05
     clon
    1.03
    ानि
    1.03
    POSITIVE LOGITS
    ̯
    1.73
    ̆
    1.66
    спользу
    1.39
    ßer
    1.36
    ଁ
    1.29
    per
    1.29
    瑁
    1.28
    এর
    1.26
    ਂ
    1.22
    спользование
    1.20
    Activations Density 0.116%

    No Known Activations