© 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. 40-GEMMASCOPE-2-RES-262K
    7. 34715
    Prev
    Next
    INDEX
    Explanations

    trained model concepts

    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_40_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
     Transactions
    0.46
     candidature
    0.46
     બે
    0.41
     busiest
    0.41
     उभ
    0.41
    iremos
    0.40
     🙂
    0.40
    ylmethylsulfanyl
    0.40
    vedad
    0.39
     transactions
    0.39
    POSITIVE LOGITS
    Fors
    0.40
    Sund
    0.40
    廣場
    0.39
    带来的
    0.38
    OnUiThread
    0.38
    砂
    0.38
    Smooth
    0.37
    Kent
    0.37
    绑
    0.37
    预
    0.36
    Activations Density 0.000%

    No Known Activations