© 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. 11705
    Prev
    Next
    INDEX
    Explanations

    plant matter and medical terms

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

    scientific or technical terms and identifiers in research papers or technical documents.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron consistently activates on domain‐specific technical terms and acronyms (e.g. specialized nouns like “Noni,” “Ference,” “meta data,” “EPAC,” “PKA,” “sensors”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    presumably
    -2.31
    despite
    -2.14
    {}
    -2.08
    particularly
    -2.03
    isait
    -2.03
    itisation
    -1.97
    criminate
    -1.96
    mating
    -1.96
     Dinas
    -1.94
    quisition
    -1.93
    POSITIVE LOGITS
     both
    2.66
     several
    2.34
     some
    2.34
     there
    2.28
     used
    2.14
     using
    2.13
     our
    2.11
     and
    2.09
     when
    2.06
    When
    2.06
    Activations Density 0.254%

    No Known Activations