© 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. 34-GEMMASCOPE-RES-131K
    7. 84145
    Prev
    Next
    INDEX
    Explanations

    medical or scientific terms

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

    nouns that represent items, objects, or data being transferred, transmitted, or processed.

    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_34/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
     and
    -1.22
     manguera
    -1.17
     millón
    -1.10
    dő
    -1.05
    Geografie
    -1.05
    unse
    -1.04
    {{{
    -1.03
    pecting
    -1.02
     néanmoins
    -1.02
     rápidamente
    -1.02
    POSITIVE LOGITS
    ちなみに
    1.04
     aforesaid
    0.95
     on
    0.94
    を
    0.93
    %,
    0.91
    とにかく
    0.90
    in
    0.90
    ha
    0.88
    ただし
    0.88
    참고
    0.88
    Activations Density 0.192%

    No Known Activations