© 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. 110561
    Prev
    Next
    INDEX
    Explanations

    listing substances and materials

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

    scientific or technical terms in explanatory contexts such as chemical compounds, substances, and their properties.

    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
    OnePlus
    -1.00
    tigste
    -0.95
    banez
    -0.93
    verticalLayout
    -0.91
    Renault
    -0.88
    poem
    -0.88
     Skincare
    -0.87
     OnePlus
    -0.87
    sigen
    -0.86
     إذا
    -0.85
    POSITIVE LOGITS
     many
    1.20
     both
    1.15
     commercially
    1.14
     commonly
    1.13
     most
    1.12
     our
    1.07
     certain
    1.05
     some
    0.98
     that
    0.92
     common
    0.92
    Activations Density 0.138%

    No Known Activations