© 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. 10-GEMMASCOPE-RES-131K
    7. 65675
    Prev
    Next
    INDEX
    Explanations

    positive reviews and feedback

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

    This neuron detects strongly positive or praising sentiment words (e.g. “wonderful,” “amazing,” “brilliant”) in reviews.

    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
     to
    -1.98
     alcuni
    -1.55
    </h1>
    -1.51
     alcune
    -1.50
     многих
    -1.41
    sightly
    -1.40
     Algunos
    -1.38
     molti
    -1.38
    などで
    -1.38
     einige
    -1.33
    POSITIVE LOGITS
    互联网档案馆
    1.57
     eterno
    1.46
    Despite
    1.43
     parvenir
    1.42
    Another
    1.37
    ти
    1.37
    larla
    1.37
    Although
    1.36
     её
    1.36
    ”、“
    1.35
    Activations Density 0.024%

    No Known Activations