© 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-65K
    7. 4783
    Prev
    Next
    INDEX
    Explanations

    solve, improve, access, explain

    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_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
     somebody
    1.06
    某种
    0.93
    某个
    0.93
     someone
    0.91
     någon
    0.91
    某
    0.90
     alguém
    0.89
     alguien
    0.89
     ciertas
    0.87
     something
    0.85
    POSITIVE LOGITS
    与
    0.84
    不仅
    0.81
     advancements
    0.80
    both
    0.77
    шев
    0.76
    दोनों
    0.75
    available
    0.74
    與
    0.74
    advanced
    0.73
    لا
    0.73
    Activations Density 0.216%

    No Known Activations