© 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. 234127
    Prev
    Next
    INDEX
    Explanations

    edible species

    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
     адам
    0.46
     транспорта
    0.46
     imigr
    0.46
     συμμε
    0.43
     eléctricas
    0.43
     energía
    0.42
    Пи
    0.42
    苎
    0.42
    带有
    0.41
    电机
    0.41
    POSITIVE LOGITS
     COVID
    0.46
    hline
    0.45
    uggest
    0.43
     Букмекерская
    0.43
    ispiels
    0.43
    uka
    0.43
    ಿಕ
    0.42
    ષ્ય
    0.42
     ましょう
    0.41
     Ballon
    0.41
    Activations Density 0.002%

    No Known Activations