© 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. 22-GEMMASCOPE-RES-131K
    7. 67595
    Prev
    Next
    INDEX
    Explanations

    non-English stock terms

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

    The neuron fires most strongly on relationship‐expressing function words—prepositions like “to,” “with,” “on,” “from,” “as,” “across,” 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_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
    Here
    -1.02
    雖
    -1.01
    ujuk
    -1.00
     visibly
    -0.99
    會有
    -0.95
    兩
    -0.94
    會
    -0.93
     brilho
    -0.92
    All
    -0.92
     uszkod
    -0.92
    POSITIVE LOGITS
     papiers
    1.16
     fokus
    1.11
     siè
    1.11
     abonnement
    1.11
     kopen
    1.07
    breo
    1.05
     risiko
    1.05
     indien
    1.03
     relat
    1.02
     stockfoto
    1.01
    Activations Density 0.147%

    No Known Activations