© 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. 836
    Prev
    Next
    INDEX
    Explanations

    past tense verbs and negations

    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
    icelli
    0.68
     الأخرى
    0.59
    ână
    0.56
    ソコン
    0.55
    ន្ថ
    0.54
    <unused1839>
    0.53
     بالإضافة
    0.53
     Daarna
    0.51
    ことも
    0.51
    !).
    0.51
    POSITIVE LOGITS
     didnt
    0.74
     doesnt
    0.68
     didn
    0.67
     เคย
    0.67
     saw
    0.66
     видел
    0.65
     seems
    0.64
    didn
    0.63
     drove
    0.62
    俺
    0.62
    Activations Density 0.004%

    No Known Activations