© 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-TRANSCODER-262K
    7. 219556
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by auxiliary verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    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
    Previously
    0.35
     initially
    0.35
    以前
    0.35
     ಹಿಂದೆ
    0.34
     раньше
    0.34
     previously
    0.34
     गुजरात
    0.33
    み
    0.33
     হয়
    0.32
    みに
    0.32
    POSITIVE LOGITS
     contest
    0.36
     Benedict
    0.34
    concatenate
    0.34
     immerse
    0.32
     immersing
    0.32
    Tapi
    0.32
     quién
    0.30
     menek
    0.30
     Janata
    0.30
     acquaintance
    0.29
    Activations Density 0.001%

    No Known Activations