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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129587
    Prev
    Next
    INDEX
    Explanations

    substances and their characteristics

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

    The neuron detects the word "substances" and related contexts, particularly when substances are being described, classified, or discussed in scientific or technical contexts.

    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_10/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
    毉
    -2.42
     твоя
    -2.38
    𓋼
    -2.33
    鸶
    -2.30
    ឍ
    -2.25
    떳
    -2.25
    вгений
    -2.23
    archiwizowane
    -2.20
    ㉕
    -2.20
     ddelwed
    -2.19
    POSITIVE LOGITS
    ↵↵
    2.42
    }
    2.30
    ли
    2.28
    ть
    2.13
     organize
    2.02
    2
    1.94
    ześnie
    1.88
     improve
    1.88
    响起
    1.87
     you
    1.85
    Activations Density 0.013%

    No Known Activations