© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35702
    Prev
    Next
    INDEX
    Explanations

    He or she followed by a 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/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
     Spy
    0.37
     πυ
    0.37
    吵
    0.34
     গতি
    0.33
    ListItem
    0.33
     Ли
    0.33
     обязан
    0.33
    પ્ત
    0.33
    ған
    0.33
    嫖
    0.33
    POSITIVE LOGITS
     scissors
    0.36
     herramientas
    0.36
    ழுக
    0.36
    歡迎
    0.35
    Scissors
    0.35
    TOOLS
    0.35
    scissors
    0.35
    tools
    0.34
    NOM
    0.34
    ))`
    0.34
    Activations Density 0.012%

    No Known Activations