© 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-RES-262K
    7. 4862
    Prev
    Next
    INDEX
    Explanations

    ' t' follows quote

    np_acts-logits-general · gemini-2.5-flash-lite

    uses of the curly apostrophe (right single quotation mark) in English contractions.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    io
    0.35
     one
    0.32
    utils
    0.32
    error
    0.32
    data
    0.31
    <unused2164>
    0.31
     för
    0.30
     we
    0.30
    }$.
    0.29
     sont
    0.29
    POSITIVE LOGITS
     ג
    0.32
     ſ
    0.32
    Justice
    0.30
     ا
    0.29
     م
    0.29
    нам
    0.28
    ؤ
    0.28
    сыпа
    0.27
    తన
    0.27
    Pharmac
    0.26
    Activations Density 0.206%

    No Known Activations