© 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. 102354
    Prev
    Next
    INDEX
    Explanations

    curb or sidewalk

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

    The neuron fires strongly on occurrences of “curb” or “curbside” (references to the curb).

    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
     trenes
    -0.75
     hexadecimal
    -0.70
    ungal
    -0.69
    殿
    -0.67
    ρού
    -0.67
     zaken
    -0.67
    回
    -0.67
    Styleable
    -0.66
    λεκ
    -0.66
    жений
    -0.66
    POSITIVE LOGITS
     curb
    4.69
     Curb
    3.36
     curbs
    3.23
     ker
    2.69
    cur
    2.52
     cur
    2.34
    Cur
    2.27
     Cur
    1.91
     CUR
    1.87
     sidewalk
    1.78
    Activations Density 0.024%

    No Known Activations