© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 66175
    Prev
    Next
    INDEX
    Explanations

    iterate with index or key

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

    The neuron fires on tokens that name or indicate loop/index variables or enumeration counters (e.g. “idx,” “i,” “index,” “enumerate”).

    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
     there
    -0.97
    ;
    -0.88
     kiedy
    -0.86
    哙
    -0.80
    ですかね
    -0.78
     Kiedy
    -0.77
     vrijdag
    -0.77
    でしょうね
    -0.77
    Usuario
    -0.76
    providedIn
    -0.76
    POSITIVE LOGITS
    gever
    0.92
     them
    0.91
    Preface
    0.90
     peup
    0.86
    罫
    0.86
     monkey
    0.85
    ◢
    0.84
     quels
    0.84
    бливості
    0.82
    Silent
    0.81
    Activations Density 0.002%

    No Known Activations