© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 76030
    Prev
    Next
    INDEX
    Explanations

    file dialogs in python

    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
    elder
    0.46
    ille
    0.46
    ê
    0.45
    iy
    0.44
    ivot
    0.43
    ]:
    0.43
    jä
    0.43
    mern
    0.42
    .:
    0.42
    lord
    0.42
    POSITIVE LOGITS
     неу
    0.49
     выполнение
    0.47
     выполнения
    0.47
     ускори
    0.46
    โดย
    0.45
    ड
    0.44
    良好的
    0.44
     мнение
    0.43
     де
    0.43
    态度
    0.43
    Activations Density 0.001%

    No Known Activations