© 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. 110514
    Prev
    Next
    INDEX
    Explanations

    emissions and reactants

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

    technical terminology related to industrial processes, particularly fuel processing, combustion systems, and chemical engineering.

    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
    spira
    -0.75
     hydrocarbon
    -0.74
    zación
    -0.70
    <0xF1>
    -0.69
    وظ
    -0.69
     ETH
    -0.68
     graphene
    -0.67
     hydrocarbons
    -0.67
    ErrorType
    -0.67
    atmosphère
    -0.66
    POSITIVE LOGITS
    esper
    0.82
     injected
    0.82
     injec
    0.75
    injection
    0.75
    injected
    0.73
    الي
    0.71
    hydrated
    0.71
    ESP
    0.70
     electrostatic
    0.70
    خدا
    0.70
    Activations Density 0.026%

    No Known Activations