© 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. 128334
    Prev
    Next
    INDEX
    Explanations

    men and

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

    The neuron fires on mentions of gendered groups or terms (e.g. “women,” “men,” “girls,” “boys”).

    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
     
    -3.17
    ”
    -2.66
    ]
    -2.53
     Gegenteil
    -2.31
     They
    -2.31
     ’
    -2.30
     “
    -2.27
    ll
    -2.27
    …”
    -2.25
    are
    -2.19
    POSITIVE LOGITS
    鯔
    2.58
    ࣭
    2.58
    沩
    2.56
    鶺
    2.52
    蕯
    2.50
    狲
    2.47
     Ако
    2.42
     入り口
    2.38
    </i>
    2.36
    涠
    2.34
    Activations Density 0.051%

    No Known Activations