© 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. 40-GEMMASCOPE-2-RES-262K
    7. 136514
    Prev
    Next
    INDEX
    Explanations

    to the past

    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
     инициа
    0.38
    نج
    0.38
    峰
    0.38
    าด
    0.37
     iniz
    0.37
     보다
    0.36
    极限
    0.36
    мония
    0.36
    算
    0.36
    Initializer
    0.35
    POSITIVE LOGITS
     goodwill
    0.42
    百貨
    0.41
     goo
    0.41
     dilute
    0.41
     loosen
    0.40
     uphill
    0.39
     facilit
    0.39
     scholarly
    0.39
    𝐊
    0.39
     Bonjour
    0.39
    Activations Density 0.013%

    No Known Activations