© 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. 31301
    Prev
    Next
    INDEX
    Explanations

    automotive parts and systems

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

    aftermarket customizations and LoRA

    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
    培養
    0.46
    โรค
    0.46
    占い
    0.45
     anticoag
    0.45
     mediated
    0.45
    新聞
    0.44
    タリ
    0.44
    ㄛ
    0.44
     psychiat
    0.43
    物質
    0.43
    POSITIVE LOGITS
     aftermarket
    0.85
     Fahrzeug
    0.77
    車種
    0.75
     installers
    0.74
     automakers
    0.73
     automotive
    0.71
     OEM
    0.71
     Motorsports
    0.71
     Vehicle
    0.70
     গাড়
    0.69
    Activations Density 0.144%

    No Known Activations