© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 23749
    Prev
    Next
    INDEX
    Explanations

    pre- and post- event medical assessments

    np_acts-logits-general · gemini-2.5-flash-lite

    prefixes and terms related to stages before a main process or event (pre-, post-, launch, start, etc.).

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    Ted
    -0.99
    えっ
    -0.95
    pecific
    -0.93
     persoons
    -0.90
    tains
    -0.90
     daarbij
    -0.90
     naast
    -0.88
     می‌کن
    -0.88
    omat
    -0.88
    响应
    -0.88
    POSITIVE LOGITS
     period
    1.35
     phase
    1.15
     stage
    1.08
     activities
    1.05
     era
    0.98
     scenario
    0.98
     assessment
    0.94
     strategy
    0.91
     investigation
    0.90
     evaluation
    0.89
    Activations Density 0.075%

    No Known Activations