© 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. 34-GEMMASCOPE-RES-131K
    7. 58076
    Prev
    Next
    INDEX
    Explanations

    housing and residences

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

    This neuron is specialized to pick out numeric tokens (digits, numbers, and numeric sequences) 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_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
     imprisoned
    -0.81
    慶
    -0.81
    шко
    -0.79
    itch
    -0.79
     ます
    -0.78
    स्क
    -0.74
    askins
    -0.73
     podczas
    -0.73
     techniques
    -0.72
    Control
    -0.71
    POSITIVE LOGITS
     house
    1.80
     housing
    1.55
     houses
    1.55
     residence
    1.38
     House
    1.32
     residential
    1.27
    house
    1.20
    residence
    1.20
    House
    1.19
     HOUSE
    1.19
    Activations Density 0.021%

    No Known Activations