© 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. 13133
    Prev
    Next
    INDEX
    Explanations

    star ratings

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

    The neuron fires on numeric review scores, especially star‐rating expressions (e.g. “5‐star,” “4 stars,” 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
     sebagainya
    -1.25
    лючение
    -1.19
     leuke
    -1.12
     daarom
    -1.12
     cyclisme
    -1.11
    쫓
    -1.09
     sekitar
    -1.09
     イオン
    -1.09
     beendet
    -1.07
     ſont
    -1.06
    POSITIVE LOGITS
     for
    1.39
     on
    1.30
     rating
    1.13
    。　
    1.12
     service
    1.10
     effort
    1.10
     intention
    1.09
     addiction
    1.08
     komentar
    1.07
    ="
    1.06
    Activations Density 0.006%

    No Known Activations