© 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. 8957
    Prev
    Next
    INDEX
    Explanations

    explain or clarify points

    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
    ே
    2.70
    er
    2.42
     verá
    2.31
    у
    2.31
    ид
    2.26
    り
    2.20
    o
    2.17
    ীর
    2.16
     deliciously
    2.14
    ্ক
    2.13
    POSITIVE LOGITS
    ون
    2.72
    擊
    2.71
    人士
    2.54
    ITECTURE
    2.27
    𝚕
    2.24
     зрения
    2.23
    ی
    2.21
    𝚘
    2.19
    edly
    2.18
    𝚝
    2.12
    Activations Density 0.310%

    No Known Activations