© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 139326
    Prev
    Next
    INDEX
    Explanations

    question endings with 's'

    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
    inghouse
    0.48
     Eigen
    0.47
    俑
    0.46
    onics
    0.46
     ప్ర
    0.46
     Issue
    0.45
     життя
    0.45
     Convent
    0.44
     químico
    0.44
     Happ
    0.44
    POSITIVE LOGITS
    {
    0.43
    W
    0.42
     interrupts
    0.42
    Whilst
    0.41
    X
    0.40
     interruptions
    0.39
    unoscut
    0.39
    ́c
    0.39
    Unknown
    0.38
    whereas
    0.38
    Activations Density 0.003%

    No Known Activations