Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-65K
    4. 47047
    Prev
    Next
    INDEX
    Explanations

    King of X, royal titles

    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_65k_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
     terpen
    2.43
    情况下
    2.43
    𝘬
    2.41
     Конгрегация
    2.24
    ্নি
    2.23
     coiled
    2.21
    发展的
    2.21
     trophic
    2.21
     передачи
    2.21
    𝘻
    2.16
    POSITIVE LOGITS
    fisher
    2.38
    া
    2.27
    pin
    2.09
     ἐν
    2.09
    a
    2.02
    ما
    1.98
    evším
    1.98
    liness
    1.94
    se
    1.93
    señ
    1.93
    Activations Density 0.079%

    No Known Activations