© 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. 22-GEMMASCOPE-RES-131K
    7. 64888
    Prev
    Next
    INDEX
    Explanations

    parents and family texts

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

    The main thing this neuron does is detect mentions of parents (the words “parent(s)” or closely related forms).

    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
    '
    -2.75
     '
    -2.66
    ,'
    -2.30
     in
    -2.23
    “
    -2.13
    i
    -2.05
     This
    -2.00
    ('
    -1.98
    ]
    -1.95
     got
    -1.93
    POSITIVE LOGITS
    槩
    2.84
    ﹍﹍
    2.83
    淠
    2.75
    鱚
    2.63
    ться
    2.53
    鮠
    2.50
     parachoque
    2.45
    Ꭳ
    2.38
    Debido
    2.25
    Luego
    2.22
    Activations Density 0.017%

    No Known Activations