© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 71684
    Prev
    Next
    INDEX
    Explanations

    data annotation and programming constructs

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

    The neuron activates on uncommon, domain-specific keywords or identifiers (e.g. library/class names, annotations, or technical terms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     from
    -1.76
    之后
    -1.66
     WITH
    -1.65
     lancia
    -1.64
     dengan
    -1.59
    之後
    -1.54
    嘍
    -1.52
    änemark
    -1.48
     With
    -1.44
    borderSide
    -1.42
    POSITIVE LOGITS
    <bos>
    1.63
    星人
    1.44
     “
    1.38
     foram
    1.30
    攫
    1.29
    kker
    1.28
     véri
    1.25
     montrer
    1.25
    ↵
    1.24
     inic
    1.24
    Activations Density 0.000%

    No Known Activations