© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 72775
    Prev
    Next
    INDEX
    Explanations

    wherever they go or are

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

    The neuron fires on locative adverbial phrases that begin with “where” or “wherever” followed by a pronoun and verb (e.g. “wherever you go,” “where they live,” “wherever it can be found”).

    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
    橚
    -1.71
    𓆏
    -1.66
    镲
    -1.59
    
    -1.58
    桖
    -1.55
    蜴
    -1.53
    でしたが
    -1.49
     totalement
    -1.48
    ");
    -1.47
     kapture
    -1.47
    POSITIVE LOGITS
     it
    2.33
    包子
    1.66
     new
    1.64
     changing
    1.63
     different
    1.63
     theres
    1.55
     varying
    1.51
    f
    1.51
     recieve
    1.50
    in
    1.46
    Activations Density 0.007%

    No Known Activations