Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11663
    Prev
    Next
    INDEX
    Explanations

    enumeration and other lists

    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
     needed
    -1.20
     zahl
    -1.13
     evening
    -1.13
     necessary
    -1.09
     year
    -1.09
     religione
    -1.05
     food
    -1.03
     week
    -1.02
     section
    -1.02
    ή
    -1.00
    POSITIVE LOGITS
    éfonos
    1.26
    others
    1.18
    וּ
    1.14
    endalikan
    1.13
     others
    1.03
    Страна
    1.01
     інші
    0.99
     ა
    0.95
    Others
    0.94
    ૭
    0.94
    Activations Density 0.037%

    No Known Activations