© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 1050
    Prev
    Next
    INDEX
    Explanations

    if clauses

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

    periods at the end of sentences.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    persuasive or evaluative language that emphasizes importance, responsibility, or urges action.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    했고
    0.66
    早在
    0.58
     कक्क
    0.55
    并通过
    0.55
    भीर
    0.54
    lemish
    0.53
    useks
    0.52
    であり
    0.52
    چہ
    0.52
    товано
    0.52
    POSITIVE LOGITS
     if
    5.81
     если
    5.25
     nếu
    5.09
     якщо
    4.94
     dacă
    4.75
     jika
    4.72
     إذا
    4.59
     jeśli
    4.59
    if
    4.56
    ถ้า
    4.53
    Activations Density 2.744%

    No Known Activations