© 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. 17-GEMMASCOPE-2-RES-16K
    4. 362
    Prev
    Next
    INDEX
    Explanations

    excited to

    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
    ب
    0.61
     illa
    0.58
    и
    0.52
     प्रकारे
    0.52
    ри
    0.51
    ﺏ
    0.49
    Chú
    0.49
    ек
    0.49
    də
    0.49
    identical
    0.48
    POSITIVE LOGITS
    忡
    0.75
    जनक
    0.75
     Sincerely
    0.70
     doubting
    0.69
    不安
    0.68
     Frankly
    0.65
     suspicions
    0.65
     خاطر
    0.62
    lessly
    0.62
    <0x9E>
    0.61
    Activations Density 1.442%

    No Known Activations