© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11531
    Prev
    Next
    INDEX
    Explanations

    Tesla, electric cars, EVs

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

    Tesla, electric vehicles, Elon Musk

    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_40_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
     carbohyd
    0.50
    腹
    0.49
     FUEL
    0.45
    abdominal
    0.45
     abdominal
    0.44
     хро
    0.43
     Darlington
    0.42
    磧
    0.42
     сей
    0.41
     亠
    0.41
    POSITIVE LOGITS
     Tesla
    1.71
    Tesla
    1.64
     tesla
    1.59
     electric
    1.48
    特斯拉
    1.45
     इलेक्ट्रिक
    1.41
     EV
    1.35
    Electric
    1.35
     EVs
    1.35
     Electric
    1.34
    Activations Density 0.122%

    No Known Activations