© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11488
    Prev
    Next
    INDEX
    Explanations

    acts of service and charity

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    風險
    -1.04
     certamen
    -0.99
     aparcamiento
    -0.99
    Fatalf
    -0.96
    FromNib
    -0.93
    ブログ村
    -0.93
    seguida
    -0.93
     técnicas
    -0.92
     respaldo
    -0.92
    Стоимость
    -0.91
    POSITIVE LOGITS
     charity
    1.66
     volunteer
    1.38
     altru
    1.36
     charitable
    1.34
     humanitarian
    1.14
     donation
    1.06
     donations
    1.06
    charity
    1.05
    Charity
    1.05
    ungguh
    1.05
    Activations Density 0.053%

    No Known Activations