© 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. 13697
    Prev
    Next
    INDEX
    Explanations

    family members' relationships

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

    This neuron detects words referring to people’s homes or family relationships (e.g., house, hometown, mother, father, sister, spouse).

    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
     Wavelength
    -1.17
    ⢧
    -1.16
    iqué
    -1.16
     naše
    -1.14
     fasse
    -1.14
    ländischen
    -1.11
     ngàn
    -1.09
    lüğü
    -1.07
     sabbath
    -1.06
    以上です
    -1.05
    POSITIVE LOGITS
     them
    1.30
    The
    1.23
    depends
    1.13
     verring
    1.13
     $
    1.09
    They
    1.05
     obra
    1.05
     They
    1.05
    ano
    1.04
    Never
    1.04
    Activations Density 0.150%

    No Known Activations