© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 53823
    Prev
    Next
    INDEX
    Explanations

    all walks of life

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

    The neuron activates on phrases that describe people coming “from … walk(s) of life,” i.e. mentions of diverse backgrounds.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     tige
    -0.86
    ;">
    -0.85
    蔘
    -0.84
    IVID
    -0.81
     chimiques
    -0.81
    Styleable
    -0.77
    tiga
    -0.75
     vpon
    -0.74
    trzyma
    -0.73
    潴
    -0.73
    POSITIVE LOGITS
     walks
    4.13
     walk
    3.27
    walks
    2.80
     Walks
    2.69
    walk
    2.66
     Walk
    2.45
     walked
    2.41
    Walk
    2.39
     WALK
    2.08
    WALK
    1.77
    Activations Density 0.026%

    No Known Activations