© 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. 677
    Prev
    Next
    INDEX
    Explanations

    Spanish/French noun phrases

    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
    一个
    1.18
    ת
    0.81
    en
    0.77
    に
    0.77
    து
    0.74
    就是
    0.73
    tains
    0.73
     coprime
    0.72
    ف
    0.72
    duced
    0.71
    POSITIVE LOGITS
    𝓼
    0.77
    بی
    0.66
     scenarios
    0.66
    トライ
    0.66
     Verteid
    0.66
    ни
    0.66
    த்தகைய
    0.65
    ники
    0.64
    usions
    0.63
    โอ
    0.63
    Activations Density 0.188%

    No Known Activations