© 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. 60826
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code

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

    This neuron activates on dash characters (hyphens), especially when they appear as leading list‐item markers.

    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
     over
    -1.22
     from
    -1.18
    家を
    -0.98
     as
    -0.98
    家は
    -0.98
     massively
    -0.96
     just
    -0.96
     within
    -0.95
     through
    -0.93
     showed
    -0.93
    POSITIVE LOGITS
     inhalt
    1.15
     interrom
    1.09
    ほんとに
    1.04
     alcuni
    1.04
    皞
    1.03
     miesto
    1.02
    ENSIONS
    1.02
     efekty
    0.98
     startling
    0.98
    ほんと
    0.97
    Activations Density 0.020%

    No Known Activations