© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3773
    Prev
    Next
    INDEX
    Explanations

    car makes and models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_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
    电机
    1.30
     lubricating
    1.27
     homeopathy
    1.24
    idges
    1.21
     Briggs
    1.20
    koch
    1.16
    솥
    1.16
    とう
    1.15
     thermodynamic
    1.15
    boiler
    1.15
    POSITIVE LOGITS
     inmate
    1.43
     Bisc
    1.42
     frosted
    1.41
     felon
    1.40
     legalization
    1.39
    Arizona
    1.39
     Arizona
    1.38
     scarlet
    1.34
     draped
    1.31
     maroon
    1.30
    Activations Density 0.157%

    No Known Activations