© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 1195
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and equations

    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_16k_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
     comorbid
    1.70
    거나
    1.69
    듯이
    1.52
    ))_{
    1.45
    ">−</
    1.42
     distressing
    1.41
     دیگر
    1.38
    듯
    1.37
    𝘢
    1.36
     traff
    1.36
    POSITIVE LOGITS
     zorgt
    1.44
     conviene
    1.43
     perlu
    1.40
    pä
    1.40
    ourcen
    1.38
    jangan
    1.37
     punten
    1.29
     bildet
    1.28
     Anniversary
    1.28
    hitung
    1.27
    Activations Density 0.502%

    No Known Activations