© 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
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 736
    Prev
    Next
    INDEX
    Explanations

    conjunctions and list separators

    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
    ?,?,
    0.94
     др
    0.81
    ദം
    0.78
    <unused49>
    0.77
    ωτερ
    0.76
    iranje
    0.75
    <unused42>
    0.75
    ട്ടം
    0.74
     zugleich
    0.73
    <unused72>
    0.72
    POSITIVE LOGITS
     and
    4.60
     और
    4.23
    และ
    4.20
     आणि
    4.10
     и
    4.05
     અને
    3.98
     và
    3.97
     এবং
    3.94
    和
    3.85
     ಮತ್ತು
    3.82
    Activations Density 0.847%

    No Known Activations