© 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. 1436
    Prev
    Next
    INDEX
    Explanations

    the word "plus"

    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
    т
    1.28
    ت
    1.19
    𝑈
    0.98
    קום
    0.94
    бле
    0.92
    tok
    0.90
    詁
    0.88
    OutOf
    0.88
    ק
    0.88
    \|
    0.87
    POSITIVE LOGITS
     crucially
    1.31
     whatever
    1.26
     ça
    1.21
     tard
    1.17
     extras
    1.14
     oczywiście
    1.14
    チック
    1.13
     nifty
    1.13
     hefty
    1.10
     bonus
    1.09
    Activations Density 0.001%

    No Known Activations