© 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. 34-GEMMASCOPE-RES-131K
    7. 64410
    Prev
    Next
    INDEX
    Explanations

    compound nouns and phrases

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

    The neuron activates strongly on any form of “crowd”-related words (e.g. crowd, crowds, crowdsourcing).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     تیم
    -0.77
    adder
    -0.76
    situ
    -0.75
    imbursement
    -0.75
    sino
    -0.73
    ridges
    -0.73
    PopUp
    -0.73
     geschickt
    -0.71
     Rad
    -0.71
     Gable
    -0.70
    POSITIVE LOGITS
    ])]
    0.86
    map
    0.78
     Übers
    0.75
    print
    0.71
    ólogos
    0.70
    play
    0.69
    atura
    0.68
    anças
    0.68
    maps
    0.68
    角落
    0.68
    Activations Density 0.077%

    No Known Activations