© 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. 40-GEMMASCOPE-2-RES-65K
    7. 1003
    Prev
    Next
    INDEX
    Explanations

    tomato and its forms

    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_40_width_65k_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
     jumped
    0.46
    parquet
    0.44
     snowflake
    0.43
    잣
    0.42
     Snowflake
    0.39
    Histogram
    0.39
    {:
    0.39
     snowflakes
    0.39
     manque
    0.39
     leaped
    0.39
    POSITIVE LOGITS
     tomato
    1.30
     Tomato
    1.25
    Tomato
    1.20
    tomato
    1.20
     tomatoes
    1.17
     टमाटर
    1.16
     Tomatoes
    1.15
    🍅
    1.12
     tomate
    1.05
     tomat
    1.01
    Activations Density 0.082%

    No Known Activations