© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130161
    Prev
    Next
    INDEX
    Explanations

    mother

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

    The main thing this neuron does is detect mentions of “mother” in the text.

    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
    f
    -1.75
     on
    -1.65
    u
    -1.59
    ”
    -1.53
    j
    -1.49
    v
    -1.46
    k
    -1.45
    s
    -1.44
    c
    -1.39
    p
    -1.39
    POSITIVE LOGITS
    dengan
    1.38
     höl
    1.36
    tling
    1.34
    Trayectoria
    1.34
    untuk
    1.30
    requirements
    1.27
    aways
    1.27
    menü
    1.27
     elementy
    1.23
    GEBURTS
    1.23
    Activations Density 0.024%

    No Known Activations