© 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. 22-GEMMASCOPE-RES-131K
    7. 27155
    Prev
    Next
    INDEX
    Explanations

    finding something

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

    The neuron activates on occurrences of the past‐tense verb “found,” especially in “I found …” phrases indicating discovery.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    時には
    -1.22
     которого
    -1.18
     которых
    -1.13
     I
    -1.06
     которой
    -1.01
     или
    -0.95
    確認ください
    -0.94
     views
    -0.94
     beliebtesten
    -0.92
     میں
    -0.92
    POSITIVE LOGITS
     through
    1.39
     that
    1.35
     huiles
    1.24
     œufs
    1.23
    寐
    1.20
    找到了
    1.13
    引用元
    1.12
    Enfin
    1.12
    どうやら
    1.11
    ppone
    1.10
    Activations Density 0.037%

    No Known Activations