© 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. 22-GEMMASCOPE-RES-131K
    7. 70982
    Prev
    Next
    INDEX
    Explanations

    match and similarity

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

    The neuron is triggered by any occurrence of the substring “match” (in words like “match,” “Match,” “matches,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     hakkında
    -0.95
    untuk
    -0.94
     Questo
    -0.92
     preval
    -0.92
     about
    -0.90
    finale
    -0.90
     aplicativos
    -0.90
    nend
    -0.88
     indepen
    -0.88
    ータル
    -0.88
    POSITIVE LOGITS
    match
    1.11
     matching
    1.11
     match
    1.05
     with
    1.02
     closeness
    1.01
     undeniably
    0.99
    匹配
    0.99
    درسة
    0.96
     lantaran
    0.95
     matches
    0.91
    Activations Density 0.047%

    No Known Activations