© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84954
    Prev
    Next
    INDEX
    Explanations

    regulation, movement, polymorphic, characteristics

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

    scientific or technical terms related to structure, formation, and physical properties.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     themselves
    -2.48
    partly
    -1.77
    potentially
    -1.64
     their
    -1.63
    increased
    -1.63
     are
    -1.62
    introducing
    -1.60
    EVERY
    -1.59
    increasing
    -1.59
    despite
    -1.57
    POSITIVE LOGITS
     its
    2.39
     or
    2.02
     is
    1.74
     with
    1.73
     itself
    1.66
     other
    1.65
     also
    1.65
    Even
    1.56
     more
    1.55
     that
    1.54
    Activations Density 0.337%

    No Known Activations