© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70046
    Prev
    Next
    INDEX
    Explanations

    accession number or ranges

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

    The neuron detects occurrences of the phrase “accession numbers” (i.e. mentions of database accession identifiers).

    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
    </h1>
    -2.47
     یا
    -2.39
    </h3>
    -2.39
    出す
    -2.28
     If
    -2.23
    といって
    -2.19
    ÇÃO
    -2.17
    ve
    -2.14
    كب
    -2.14
    外界
    -2.13
    POSITIVE LOGITS
    ↵
    2.72
    ing
    2.59
    
    2.36
    さっき
    2.34
     \
    2.25
    和她
    2.13
    たぶん
    2.09
    ྜ
    2.06
    认为
    2.03
    はこんな感じ
    2.03
    Activations Density 0.001%

    No Known Activations