© 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. 10-GEMMASCOPE-RES-131K
    7. 58995
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

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

    This neuron specializes in spotting parts of fully qualified names (e.g. Java package or import declarations with dot-separated identifiers).

    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
     ἄ
    -2.06
     ὁ
    -1.80
     ἔ
    -1.70
    りますが
    -1.64
     otro
    -1.59
     ἀ
    -1.56
    钼
    -1.55
    ⼿
    -1.54
     otra
    -1.48
    ⾮
    -1.48
    POSITIVE LOGITS
     different
    1.44
     nepiecieš
    1.42
                                   
    1.34
              
    1.32
     like
    1.31
    了
    1.30
    大的
    1.29
    THISDAY
    1.28
            
    1.27
     review
    1.27
    Activations Density 0.321%

    No Known Activations