© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 31903
    Prev
    Next
    INDEX
    Explanations

    grains, flour, meal

    np_acts-logits-general · gemini-2.5-flash-lite

    grains and cereals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    蛞
    0.55
    螭
    0.51
     اڈوں
    0.47
    眄
    0.47
    蜉
    0.44
     ګرځ
    0.43
    ฐาน
    0.43
     baseX
    0.43
    गोवा
    0.43
    貉
    0.43
    POSITIVE LOGITS
     wheat
    1.28
     пше
    1.27
     गेहूं
    1.20
     grains
    1.18
    wheat
    1.16
    🌾
    1.15
     grain
    1.14
    小麦
    1.13
    Wheat
    1.12
     barley
    1.10
    Activations Density 0.127%

    No Known Activations