© 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. 112949
    Prev
    Next
    INDEX
    Explanations

    inherited things

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

    phrases involving someone inheriting something, typically activating on the word "inherited" followed by what was received.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on words describing inheritance (e.g. “inherited,” “inherits,” “inheriting”).

    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
    ":
    -2.48
    sistence
    -2.03
    </u>
    -1.98
     â
    -1.92
     も
    -1.91
    漚
    -1.89
     pero
    -1.88
     '*':
    -1.84
    -"
    -1.83
    -1.80
    POSITIVE LOGITS
    s
    1.84
    utiliser
    1.77
     放題
    1.76
     sufrió
    1.75
     réinitial
    1.71
     entera
    1.69
    䊳
    1.68
    艫
    1.67
     剧照
    1.66
     niedersachsen
    1.66
    Activations Density 0.012%

    No Known Activations