© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84523
    Prev
    Next
    INDEX
    Explanations

    the word of

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

    The neuron fires on verbs (and related past-participles) that denote removal or deprivation—such as “shorn,” “stripped,” or “deprived”—especially when used with “of.”

    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
     out
    -2.00
    軼
    -1.70
     multifaceted
    -1.67
    fatti
    -1.67
    cerpt
    -1.67
    夙
    -1.66
     Légion
    -1.64
     solusi
    -1.64
     qtd
    -1.61
     \
    -1.59
    POSITIVE LOGITS
    m
    1.98
    "]();
    1.83
    趿
    1.80
    eps
    1.73
    蕺
    1.70
     galeri
    1.70
     ٢
    1.66
     abbiamo
    1.65
     magari
    1.64
    mathrm
    1.63
    Activations Density 0.006%

    No Known Activations