© 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. 109710
    Prev
    Next
    INDEX
    Explanations

    reality vs illusion

    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
     лекарства
    -1.05
     anonymous
    -0.85
     sore
    -0.84
    暗
    -0.84
     EXPRESS
    -0.83
    iosas
    -0.82
    大大
    -0.82
    diagram
    -0.81
    Diagram
    -0.81
    Anonymous
    -0.81
    POSITIVE LOGITS
     reality
    2.58
    reality
    2.08
     Reality
    1.64
     réalité
    1.59
     realidad
    1.59
     реаль
    1.56
    Reality
    1.56
     realities
    1.55
     created
    1.44
     realtà
    1.39
    Activations Density 0.034%

    No Known Activations