© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 82471
    Prev
    Next
    INDEX
    Explanations

    emit light at specific wavelengths

    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
     ideas
    0.47
    ideas
    0.44
    ames
    0.44
     delinquent
    0.44
     skyrocketing
    0.44
    c
    0.43
    ine
    0.43
     kepala
    0.43
    itars
    0.42
    a
    0.42
    POSITIVE LOGITS
    лізу
    0.48
    В
    0.48
     будь
    0.47
    +","
    0.47
    の種類
    0.47
     их
    0.46
     услуги
    0.45
    汕
    0.45
     সন্ত
    0.45
    苫
    0.45
    Activations Density 0.001%

    No Known Activations