© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43969
    Prev
    Next
    INDEX
    Explanations

    write down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dificultades
    0.47
     sinuses
    0.46
    erçe
    0.43
     publicaciones
    0.42
     periodicals
    0.41
     Monsanto
    0.41
     Caja
    0.40
    葲
    0.40
     лікар
    0.40
     جع
    0.40
    POSITIVE LOGITS
     down
    0.55
    down
    0.50
    WRITE
    0.47
    write
    0.47
     onto
    0.45
    Write
    0.45
     xuống
    0.44
    list
    0.43
     write
    0.43
     verbatim
    0.42
    Activations Density 0.029%

    No Known Activations