© 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. 110663
    Prev
    Next
    INDEX
    Explanations

    parts or locations followed by prepositions

    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
     ofthe
    -1.15
    创建一个
    -1.14
     the
    -1.09
    Filters
    -1.08
    OfThe
    -1.02
     カ
    -0.98
     manifestación
    -0.91
    beforeEach
    -0.91
    channels
    -0.90
    IT
    -0.85
    POSITIVE LOGITS
     các
    1.64
     nelle
    1.24
    したり
    1.20
     často
    1.15
     των
    1.12
     berbagai
    1.12
    各种
    1.11
    AutoModerator
    1.08
     various
    1.05
    各種
    1.03
    Activations Density 0.284%

    No Known Activations