© 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. 18865
    Prev
    Next
    INDEX
    Explanations

    purpose or function

    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
    Protocol
    0.52
    Diagram
    0.51
     piernas
    0.50
    DetailUI
    0.50
     yeux
    0.49
    ⏫
    0.47
    рены
    0.47
    রচনা
    0.46
     Adası
    0.46
    넴
    0.46
    POSITIVE LOGITS
    to
    0.59
    as
    0.44
     VARI
    0.43
     J
    0.43
     Philippine
    0.43
    。
    0.41
     T
    0.41
    if
    0.41
     Prussians
    0.40
    ш
    0.40
    Activations Density 0.001%

    No Known Activations