© 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. 110479
    Prev
    Next
    INDEX
    Explanations

    creation, annihilation, operators

    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
     Vladimir
    -0.82
     offended
    -0.77
     vertebrates
    -0.77
    funeralhome
    -0.75
    🪐
    -0.74
    setAccessible
    -0.70
    Prot
    -0.69
     fart
    -0.69
    Vladimir
    -0.69
    Universität
    -0.68
    POSITIVE LOGITS
     creation
    2.03
     annihilation
    2.00
     Creation
    1.65
    creation
    1.59
     operators
    1.47
     criação
    1.47
     annihil
    1.45
    Creation
    1.41
     creación
    1.39
     Anni
    1.38
    Activations Density 0.030%

    No Known Activations