© 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. 4907
    Prev
    Next
    INDEX
    Explanations

    numbers, ratios, or percentages

    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
    imum
    0.60
    poco
    0.58
    ])*
    0.58
     tiers
    0.57
    説明
    0.55
    const
    0.54
    讳
    0.53
    ساوي
    0.53
    ))&&(
    0.53
    Panic
    0.53
    POSITIVE LOGITS
    ′
    0.94
     ರಿಂದ
    0.93
     victoire
    0.90
     kemenangan
    0.89
     penerapan
    0.88
     verdict
    0.86
    រស
    0.83
    ️⃣
    0.83
    ′,
    0.83
     wynik
    0.80
    Activations Density 0.028%

    No Known Activations