© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1545
    Prev
    Next
    INDEX
    Explanations

    dimensions and price

    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_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
     массо
    0.96
     quantidade
    0.92
     काल
    0.86
    Dates
    0.84
    价
    0.84
    larghezza
    0.84
     erős
    0.82
    數量
    0.82
    Quantidade
    0.82
     וי
    0.81
    POSITIVE LOGITS
    是多少
    1.13
    AndTime
    1.00
    ്
    0.95
     Beverages
    0.89
    ക്കുറ
    0.85
     range
    0.85
     obsessed
    0.85
    wise
    0.85
    payer
    0.82
    वर्ग
    0.82
    Activations Density 1.102%

    No Known Activations