© 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-16K
    7. 1794
    Prev
    Next
    INDEX
    Explanations

    constructivism

    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_16k_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
     පරි
    0.51
    ſs
    0.51
     カ
    0.50
     නිර්
    0.49
     ре
    0.47
     வணிக
    0.47
     פּ
    0.46
     नक्की
    0.46
     સ્ટ
    0.45
     પછી
    0.45
    POSITIVE LOGITS
    )，
    0.48
     valves
    0.47
    Opened
    0.47
     Modifier
    0.47
    彘
    0.46
     Opened
    0.46
     radars
    0.46
    ंत
    0.45
    '].
    0.45
    یر
    0.44
    Activations Density 0.000%

    No Known Activations