© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 69963
    Prev
    Next
    INDEX
    Explanations

    stringent requirements

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

    The neuron specifically detects occurrences of the adjective “stringent.”

    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
    s
    -2.69
    </b>
    -2.42
    𖣔
    -2.31
    她
    -2.28
    such
    -2.23
    ዡ
    -2.20
    and
    -2.17
    薆
    -2.09
     maroon
    -2.09
    และ
    -2.09
    POSITIVE LOGITS
    </h3>
    2.39
    </h2>
    2.36
    ;
    2.25
    珦
    2.20
     pursuant
    2.19
     pekerjaan
    2.16
    इटम
    2.11
    $,
    2.09
     Other
    2.09
     â
    2.08
    Activations Density 0.009%

    No Known Activations