© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 85232
    Prev
    Next
    INDEX
    Explanations

    tea, olive, cacao

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

    words related to tea and plant-derived substances, especially names of tea plants, ingredients, and compounds.

    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
    Specifik
    -1.36
    Acknowledgement
    -1.33
    breite
    -1.21
    äksi
    -1.20
    Opere
    -1.19
    觔
    -1.19
    厝
    -1.18
     frutas
    -1.16
    隠れ
    -1.14
    枡
    -1.14
    POSITIVE LOGITS
     that
    2.09
    ↵↵
    1.33
    }
    1.23
     about
    1.19
     it
    1.15
    ]
    1.14
     sostenibilidad
    1.13
    From
    1.12
    По
    1.09
     From
    1.07
    Activations Density 0.048%

    No Known Activations