© 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. 44064
    Prev
    Next
    INDEX
    Explanations

    family home or room

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

    The neuron strongly activates on mentions of “family” or “families” (i.e. family-oriented contexts).

    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
    轳
    -1.85
    
    -1.83
     Encuentra
    -1.63
     kogo
    -1.55
     nuevos
    -1.55
     Suiza
    -1.51
    筠
    -1.51
    óta
    -1.50
    ZZA
    -1.50
     głó
    -1.50
    POSITIVE LOGITS
    with
    1.80
    ",
    1.73
    the
    1.63
    f
    1.60
    If
    1.55
     a
    1.54
    },
    1.52
    0
    1.51
    _
    1.50
    In
    1.47
    Activations Density 0.011%

    No Known Activations