© 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-262K
    7. 5588
    Prev
    Next
    INDEX
    Explanations

    in the months or centuries

    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
    ใน
    1.06
     in
    0.96
     इसमें
    0.95
    de
    0.90
    te
    0.90
    ໃນ
    0.88
    에
    0.88
     전달
    0.86
    În
    0.83
     insides
    0.80
    POSITIVE LOGITS
     accordance
    1.75
     conjunction
    1.62
     lieu
    1.50
     spite
    1.42
     terms
    1.37
     regards
    1.34
     addition
    1.32
     rámci
    1.25
     Brazil
    1.24
     November
    1.24
    Activations Density 0.173%

    No Known Activations