© 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. 47613
    Prev
    Next
    INDEX
    Explanations

    all my, all the, all our

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

    This neuron detects inclusive or totalizing words—quantifiers and possessives that signal “all,” “whole,” “both,” “such,” “my,” “our,” etc.

    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
     beberapa
    -0.95
    锲
    -0.94
     several
    -0.94
     卧室
    -0.93
    IENTS
    -0.90
    prechung
    -0.90
    iacute
    -0.90
    της
    -0.89
     faster
    -0.88
     liderazgo
    -0.87
    POSITIVE LOGITS
     the
    2.25
     these
    1.32
     kind
    1.30
     kinds
    1.27
     those
    1.17
     sort
    1.07
     kanskje
    1.02
    round
    1.00
    together
    0.99
     तरह
    0.98
    Activations Density 0.037%

    No Known Activations