© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19995
    Prev
    Next
    INDEX
    Explanations

    Costa Rica

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

    The neuron activates on occurrences of the substring “Costa,” as in place or proper names containing “Costa.”

    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
     verbess
    -3.33
     The
    -3.27
    渽
    -2.84
    訁
    -2.78
     funcionam
    -2.69
     regiões
    -2.67
    莇
    -2.59
     bedeut
    -2.52
     haupts
    -2.52
     ältere
    -2.47
    POSITIVE LOGITS
    s
    3.31
    ᯾
    3.08
    F
    2.70
    N
    2.70
    ，”
    2.64
    K
    2.52
    戆
    2.50
    𓄹
    2.48
    朦
    2.48
    </sup>
    2.48
    Activations Density 0.003%

    No Known Activations