© 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. 8938
    Prev
    Next
    INDEX
    Explanations

    belt and Belgian items

    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
    𝖊
    2.96
    łem
    2.93
    னம்
    2.92
    에
    2.90
    yed
    2.84
    𝚊
    2.81
     reprend
    2.81
    ellow
    2.80
    EE
    2.78
    2.74
    POSITIVE LOGITS
    ма
    3.26
    or
    3.22
    л
    3.20
    მწიფ
    3.05
    ্ডিং
    3.00
    лната
    2.87
    기간
    2.84
     allevi
    2.80
     inflicting
    2.74
    ਾਬ
    2.70
    Activations Density 0.077%

    No Known Activations