© 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. 73851
    Prev
    Next
    INDEX
    Explanations

    fresh rotten ratings

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

    The neuron activates on numeric values and quantitative data (e.g. ratings, percentages, years, counts).

    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
     chromatin
    -0.75
    ụp
    -0.75
    neau
    -0.73
     природ
    -0.72
     المعرف
    -0.71
     Pavlov
    -0.71
    prototype
    -0.69
     republished
    -0.69
    backer
    -0.69
    publicain
    -0.69
    POSITIVE LOGITS
     Rotten
    1.68
    Rotten
    1.30
    rotten
    1.23
     freshness
    1.22
     Fresh
    1.22
     fresh
    1.19
     rotten
    1.19
    fresh
    1.16
    Fresh
    1.15
     Audience
    1.14
    Activations Density 0.003%

    No Known Activations