© 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. 14439
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

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

    The neuron fires strongly on the “which was being…” pattern that marks the start of a passive‐voice relative clause.

    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
     späteren
    -0.85
     related
    -0.84
     more
    -0.84
    ⪼
    -0.81
    Unmarshal
    -0.77
    ficamente
    -0.76
    missed
    -0.75
     lamenta
    -0.75
    很赞
    -0.75
     directly
    -0.74
    POSITIVE LOGITS
     hoped
    1.21
     avait
    1.19
     שה
    1.13
     havia
    1.09
     juist
    1.08
     was
    1.05
     estava
    1.03
    говой
    0.98
     hopes
    0.98
     после
    0.96
    Activations Density 0.052%

    No Known Activations