© 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. 22-GEMMASCOPE-2-RES-262K
    7. 851
    Prev
    Next
    INDEX
    Explanations

    colon creates

    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_22_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
    H
    0.50
    D
    0.49
    rather
    0.48
    기고
    0.47
    지와
    0.47
    സും
    0.46
    人和
    0.46
    мости
    0.46
    M
    0.45
    N
    0.45
    POSITIVE LOGITS
     –
    2.06
     -
    1.91
     --
    1.83
     —
    1.80
     ->
    1.75
     -->
    1.65
     →
    1.62
     
    1.61
     :
    1.58
     ซึ่ง
    1.56
    Activations Density 0.975%

    No Known Activations