© 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-16K
    7. 475
    Prev
    Next
    INDEX
    Explanations

    with + positive accompaniment or quality

    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
     chance
    1.85
    ка
    1.75
    其他
    1.66
    ()=>{
    1.57
     tranche
    1.57
     сведения
    1.51
     separado
    1.50
    на
    1.45
    স
    1.44
    ट
    1.44
    POSITIVE LOGITS
     regard
    2.88
     regards
    2.84
    drawn
    2.58
    standing
    2.36
    drawing
    2.18
     impunity
    2.16
    DRAW
    2.10
     учетом
    2.02
     respecto
    2.00
    holds
    1.98
    Activations Density 0.481%

    No Known Activations