© 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. 66624
    Prev
    Next
    INDEX
    Explanations

    cytoplasmic components and processes

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

    The neuron identifies the word "cytoplasm" and related cellular compartments in biological contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on mentions of the cell’s cytoplasm or cytoplasmic locale.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    豨
    -2.47
    3
    -2.06
    烀
    -1.92
     encontram
    -1.89
     olhando
    -1.86
     interacción
    -1.82
     termed
    -1.80
     identificación
    -1.79
     serán
    -1.78
     intitulé
    -1.78
    POSITIVE LOGITS
    {
    2.50
    ]
    2.27
    }
    2.02
    <bos>
    1.98
    acterísticas
    1.78
     \&
    1.75
    アップデート
    1.69
    Dade
    1.66
     existe
    1.60
    !
    1.60
    Activations Density 0.048%

    No Known Activations