© 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-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 1197
    Prev
    Next
    INDEX
    Explanations

    fruits and vegetables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_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
    绻
    0.46
    㴼
    0.44
     tachy
    0.44
     PCIe
    0.43
    隷
    0.43
    悍
    0.43
     ANSI
    0.42
     паспорт
    0.42
     seism
    0.41
    啸
    0.41
    POSITIVE LOGITS
     tomatoes
    2.73
     vegetables
    2.61
     apples
    2.61
     bananas
    2.53
     fruit
    2.50
     fruits
    2.47
     Tomatoes
    2.44
     carrots
    2.42
     tomato
    2.41
     strawberries
    2.38
    Activations Density 0.183%

    No Known Activations