© 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. 85102
    Prev
    Next
    INDEX
    Explanations

    comprehension and OCT

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

    The neuron strongly activates on occurrences of the word “comprehension.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    references to comprehension, particularly in academic, educational, or cognitive-science contexts.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "comprehension" in educational or technical contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
     sentire
    -2.47
    鉕
    -2.47
    里面
    -2.31
     如果
    -2.31
     humeur
    -2.30
    瞜
    -2.28
    schedulers
    -2.27
    ementara
    -2.27
     sociala
    -2.23
    تیجه
    -2.20
    POSITIVE LOGITS
    摭
    2.89
    紧接着
    2.50
    ↵↵
    2.44
    阄
    2.33
    .
    2.30
    for
    2.28
     of
    2.23
    弍
    2.22
    屜
    2.19
     柄
    2.14
    Activations Density 0.010%

    No Known Activations