© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 646
    Prev
    Next
    INDEX
    Explanations

    imaginative descriptive language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     policymakers
    1.05
     stakeholders
    0.94
     potentially
    0.93
     actionable
    0.90
     proactively
    0.89
    📈
    0.87
     unrealistic
    0.87
    🤯
    0.85
     OpenAI
    0.85
     understandable
    0.83
    POSITIVE LOGITS
     ornate
    1.11
     leather
    1.10
     iridescent
    1.09
     gleaming
    1.04
     shimmering
    1.04
     glittering
    1.02
     oscuridad
    1.02
     glistening
    1.00
     metallic
    0.99
     dusk
    0.98
    Activations Density 0.740%

    No Known Activations