© 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. 22-GEMMASCOPE-RES-131K
    7. 68306
    Prev
    Next
    INDEX
    Explanations

    interface, changes, properties

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

    This neuron detects single nouns that name specialized domains or categories (e.g. “desert,” “mountain,” “user,” “interface,” “molecular,” “neuro,” “device,” “betting,” “quality,” etc.).

    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
    岐
    -1.41
    がある
    -1.38
    だが
    -1.27
    と
    -1.24
    は
    -1.23
    尤其是
    -1.19
    但在
    -1.19
    смотра
    -1.18
    但却
    -1.18
    <bos>
    -1.14
    POSITIVE LOGITS
     and
    2.02
    えっ
    1.70
    つづく
    1.60
    话音
    1.52
     stratég
    1.48
    おそ
    1.45
     a
    1.43
    凄く
    1.41
    ܇
    1.38
    明日は
    1.36
    Activations Density 0.181%

    No Known Activations