Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 8119
    Prev
    Next
    INDEX
    Explanations

    Leonardo da Vinci, Fibonacci, Italian

    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_9_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
    ことが
    1.94
     wszystkim
    1.90
    ल्या
    1.89
    𝐵
    1.88
    𝐴
    1.86
     thoại
    1.86
    𝓊
    1.84
    Gosudarstvennyj
    1.84
    場合
    1.83
    ために
    1.81
    POSITIVE LOGITS
    ዎች
    2.53
    т
    2.52
    로
    2.51
    tım
    2.38
    esque
    2.35
    та
    2.09
    ים
    2.07
    qa
    2.07
    に
    2.05
    ang
    2.02
    Activations Density 0.046%

    No Known Activations