© 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. 16-GEMMASCOPE-2-RES-262K
    7. 18012
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb

    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_16_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
     is
    0.77
     has
    0.73
     t
    0.67
     be
    0.67
     are
    0.66
     de
    0.60
     andere
    0.60
     heeft
    0.59
     was
    0.58
     kleine
    0.57
    POSITIVE LOGITS
    that
    0.59
    و
    0.57
    os
    0.55
    ро
    0.53
    ка
    0.53
    <0x80>
    0.52
    AN
    0.50
    i
    0.50
    чи
    0.50
    e
    0.48
    Activations Density 0.119%

    No Known Activations