© 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. 34-GEMMASCOPE-RES-131K
    7. 57980
    Prev
    Next
    INDEX
    Explanations

    3D OBJ model files

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

    The neuron fires strongly on numeric literals—tokens made up of digits (e.g. version numbers, array sizes, numeric constants).

    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
    ImageField
    -0.91
     insurance
    -0.88
    Image
    -0.84
     Images
    -0.83
     Image
    -0.83
    Images
    -0.74
    IMAGE
    -0.73
    drawImage
    -0.71
     album
    -0.71
     په
    -0.71
    POSITIVE LOGITS
     models
    1.87
     model
    1.80
    模型
    1.58
    loadModel
    1.49
     meshes
    1.47
     모델
    1.46
     modèles
    1.45
     mesh
    1.45
     модель
    1.44
    モデル
    1.40
    Activations Density 0.060%

    No Known Activations