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. 7223
    Prev
    Next
    INDEX
    Explanations

    survey, survive, surf

    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
    precio
    3.29
    falls
    3.02
    すぐ
    2.82
    น้อง
    2.75
    न
    2.58
    ორცი
    2.56
     preco
    2.53
     مطلب
    2.53
    nych
    2.45
     kelamin
    2.41
    POSITIVE LOGITS
    MBOL
    3.08
    𝘈
    2.96
    ר
    2.88
    臾
    2.83
    𝘴
    2.77
    ট
    2.77
     quaint
    2.74
    𝘰
    2.74
    𝘥
    2.72
    𝘢
    2.71
    Activations Density 0.237%

    No Known Activations