© 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. 109738
    Prev
    Next
    INDEX
    Explanations

    void onCreate

    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
     デイ
    -0.89
    궈
    -0.83
     Proyecto
    -0.80
     sayur
    -0.77
    ClassId
    -0.77
     rencontre
    -0.77
     cuisson
    -0.75
     decades
    -0.75
     TextInputType
    -0.75
    Druck
    -0.74
    POSITIVE LOGITS
     onCreate
    2.34
    onCreate
    1.64
     creation
    1.44
     Creation
    1.20
    Creation
    1.14
    creation
    1.08
     creations
    1.04
     Creator
    0.98
    ngOnInit
    0.98
     CRE
    0.94
    Activations Density 0.005%

    No Known Activations