© 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. 67340
    Prev
    Next
    INDEX
    Explanations

    family and junior relationships

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

    The neuron flags words denoting family relationships (e.g. niece, nephew, cousin).

    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
     then
    -1.42
     wszyst
    -1.21
     benach
    -1.09
    ↵↵
    -1.09
    Then
    -1.07
     control
    -1.05
    is
    -1.01
     व्य
    -1.00
     Werkzeug
    -1.00
     best
    -0.99
    POSITIVE LOGITS
    冏
    1.33
    girlfriend
    1.30
    ceptable
    1.30
    ionato
    1.27
    ulação
    1.26
    grandchildren
    1.24
    ffl
    1.23
    -------------</
    1.20
    "{\
    1.20
    vail
    1.20
    Activations Density 0.035%

    No Known Activations