© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10040
    Prev
    Next
    INDEX
    Explanations

    in a state or activity

    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_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
    de
    1.38
     внутрен
    1.37
    ين
    1.31
    ದ
    1.28
    د
    1.26
    在
    1.24
    ໃນ
    1.23
    te
    1.23
    ت
    1.21
    ب
    1.18
    POSITIVE LOGITS
     terms
    1.90
     accordance
    1.90
     vitro
    1.64
     lieu
    1.64
     conjunction
    1.62
     vivo
    1.50
     spite
    1.47
     relation
    1.43
    ositol
    1.36
     torno
    1.31
    Activations Density 0.090%

    No Known Activations