© 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. 34-GEMMASCOPE-RES-131K
    7. 118955
    Prev
    Next
    INDEX
    Explanations

    geographical regions and locations

    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_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
     Также
    -1.12
     backstory
    -1.00
    доми
    -0.94
    ਦੇ
    -0.93
     mää
    -0.91
    Şi
    -0.90
    encoded
    -0.90
     vediamo
    -0.89
     farà
    -0.89
     начин
    -0.88
    POSITIVE LOGITS
     notified
    0.96
     iterable
    0.88
     شيئ
    0.88
     armées
    0.87
     orchards
    0.87
    曲を
    0.85
     crocodile
    0.85
     Presidency
    0.84
     manchas
    0.84
     героя
    0.84
    Activations Density 0.019%

    No Known Activations