© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9604
    Prev
    Next
    INDEX
    Explanations

    considerable degree or amount

    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
    𝙧
    3.36
     orbitals
    3.20
    𝙣
    2.98
    𝙨
    2.91
    𝙠
    2.88
    える
    2.82
    𝙜
    2.78
    𝙞
    2.76
    ków
    2.76
    ින
    2.73
    POSITIVE LOGITS
    ب
    3.06
    -\
    2.89
    ן
    2.72
    ar
    2.70
     pula
    2.57
    est
    2.47
    tų
    2.30
     совершенно
    2.23
     było
    2.23
    ict
    2.20
    Activations Density 0.033%

    No Known Activations