© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99196
    Prev
    Next
    INDEX
    Explanations

    Oral inflammation, the present

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

    programming/technical terms and variable names in code contexts.

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

    The neuron detects mentions of eukaryotic translation initiation factors (e.g. “eIF2,” “eIF4A”).

    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
    3
    -2.27
    9
    -1.93
    1
    -1.83
     кілька
    -1.83
     зді
    -1.77
    8
    -1.73
     During
    -1.73
    6
    -1.70
     歳
    -1.66
    er
    -1.64
    POSITIVE LOGITS
    </strong>
    2.06
     garante
    1.75
     strategi
    1.75
     substan
    1.73
    said
    1.70
    峮
    1.70
     TÉ
    1.70
    ]
    1.69
     infantil
    1.67
     elab
    1.66
    Activations Density 0.001%

    No Known Activations