© 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. 102253
    Prev
    Next
    INDEX
    Explanations

    mechanical motor

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

    cult-like, complex, or challenging

    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
    và
    0.45
    ５
    0.45
    produksi
    0.44
    hees
    0.44
    香
    0.44
    㞱
    0.44
    表明
    0.43
    ಿನಲ್ಲಿ
    0.43
    岧
    0.43
    栖
    0.43
    POSITIVE LOGITS
    .
    0.50
     casco
    0.48
     anual
    0.48
     filtro
    0.46
     пропуска
    0.46
     cpf
    0.45
     тока
    0.45
     ambiente
    0.45
     litoral
    0.45
     схемы
    0.45
    Activations Density 0.000%

    No Known Activations