© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 1224
    Prev
    Next
    INDEX
    Explanations

    lists of itemsor numbered sequences

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

    references to structured entities and metadata—such as proper nouns, acronyms, product codes/IDs, URLs, and list or section labels—in formatted text.

    oai_token-act-pair · gpt-5
    Triggered 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
    Negative Logits
     heuristics
    0.22
     qubits
    0.22
     ansible
    0.22
     structs
    0.22
     plasmids
    0.22
     operands
    0.22
     coalgebra
    0.21
     duckys
    0.21
    }~\
    0.21
     sprites
    0.21
    POSITIVE LOGITS
    ua
    0.21
    have
    0.21
    Nav
    0.20
    imbing
    0.20
    usa
    0.19
     Following
    0.19
    fireplace
    0.19
    oma
    0.19
    news
    0.19
    natural
    0.19
    Activations Density 4.943%

    No Known Activations