© 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. 15000
    Prev
    Next
    INDEX
    Explanations

    occur or happen in a place

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

    The neuron activates on verbs and verb phrases that denote the occurrence or happening of an event (e.g. occur, occurs, happened, take place, detection at).

    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
     to
    -1.98
    皤
    -1.55
    matig
    -1.52
    amigo
    -1.50
     zoude
    -1.45
     vrienden
    -1.41
    😫
    -1.40
    сім
    -1.38
    😝
    -1.38
     Fibre
    -1.37
    POSITIVE LOGITS
    
    1.55
    鋆
    1.50
    butuhkan
    1.43
    čiau
    1.42
     могут
    1.42
     нее
    1.42
    もちろん
    1.34
     About
    1.33
    "
    1.33
     MUCH
    1.32
    Activations Density 0.029%

    No Known Activations