© 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. 34-GEMMASCOPE-RES-131K
    7. 102499
    Prev
    Next
    INDEX
    Explanations

    actions and processes

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

    The neuron detects words in their past-tense or participle form—i.e. verbs ending in “-ed.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Grüßen
    -1.76
    を
    -1.68
    と
    -1.64
    が
    -1.59
     also
    -1.59
    <bos>
    -1.56
    そして
    -1.55
    や
    -1.41
    それも
    -1.40
    も
    -1.39
    POSITIVE LOGITS
    為に
    1.91
    を行いました
    1.85
    づけ
    1.77
    ところに
    1.67
    の方に
    1.60
    さぁ
    1.59
    corrhi
    1.59
    えっ
    1.57
    久し
    1.52
    ほら
    1.52
    Activations Density 0.363%

    No Known Activations