© 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. 66660
    Prev
    Next
    INDEX
    Explanations

    women's [categories]

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

    The neuron fires strongly on the single letter “s” suffix (as in possessive or plural markers).

    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
    tonsoft
    -2.23
    
    -1.95
     poderão
    -1.91
    çou
    -1.86
    requipa
    -1.72
     Según
    -1.70
     Algunas
    -1.69
     лютого
    -1.67
    akterysty
    -1.66
    icago
    -1.63
    POSITIVE LOGITS
    m
    2.14
    "
    2.02
    C
    1.76
    </h3>
    1.71
    S
    1.62
    J
    1.61
    O
    1.54
    L
    1.53
    ↵↵
    1.52
    P
    1.51
    Activations Density 0.015%

    No Known Activations