© 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. 23981
    Prev
    Next
    INDEX
    Explanations

    fuel and gas stations

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

    fuel and gasoline stations

    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
    细胞
    0.63
    临床
    0.60
     세포
    0.56
     കഥ
    0.52
    JScripts
    0.51
    缓
    0.51
    简历
    0.50
    螅
    0.50
    expandedTitle
    0.50
    事务所
    0.50
    POSITIVE LOGITS
     fuel
    1.55
     gasoline
    1.52
     petrol
    1.37
     gasolina
    1.37
     petroleum
    1.35
    燃料
    1.34
     fuels
    1.33
     Gasoline
    1.32
    fuel
    1.30
    Fuel
    1.30
    Activations Density 0.084%

    No Known Activations