© 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. 59429
    Prev
    Next
    INDEX
    Explanations

    game object or scientific term

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

    The neuron primarily identifies numeric tokens (digits and numbers) in the document.

    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
     conclusions
    -0.75
    dorf
    -0.74
    sock
    -0.73
    葺
    -0.71
    сль
    -0.71
    getComponent
    -0.69
    privateKey
    -0.68
     webdriver
    -0.68
     المرض
    -0.67
     inescapable
    -0.67
    POSITIVE LOGITS
     GameObject
    1.98
    GameObject
    1.76
     parent
    1.23
     objects
    1.23
     prefab
    1.20
     obj
    1.20
    Parent
    1.11
    GO
    1.09
     object
    1.06
    Transform
    1.06
    Activations Density 0.014%

    No Known Activations