© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 80606
    Prev
    Next
    INDEX
    Explanations

    going through hardship

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

    The neuron activates on occurrences of “through” (and related past-participle forms like “been through,” “went through,” “gone through”), i.e. phrasal mentions of undergoing or experiencing something.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     the
    -1.52
    										
    -1.48
    									
    -1.37
                
    -1.35
     그리고
    -1.35
    I
    -1.34
     sosteniendo
    -1.32
     And
    -1.32
     realizando
    -1.31
    祼
    -1.30
    POSITIVE LOGITS
     like
    1.64
     neler
    1.51
    ↵
    1.40
    املة
    1.40
     penas
    1.40
    Seperti
    1.39
     estos
    1.38
     Když
    1.36
     renuncia
    1.35
     Seperti
    1.34
    Activations Density 0.014%

    No Known Activations