© 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. 54385
    Prev
    Next
    INDEX
    Explanations

    names, titles, descriptions

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

    The neuron activates on occurrences of the substring “name” in code (e.g. in variable or property names, selector IDs, and string literals).

    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
    They
    -1.03
    ですが
    -1.02
    z
    -0.94
     growing
    -0.93
     zahlreiche
    -0.92
    時間は
    -0.92
     probably
    -0.91
    そのため
    -0.89
     subtle
    -0.88
    r
    -0.88
    POSITIVE LOGITS
     and
    2.09
     chyb
    1.16
     muur
    1.09
     vrijdag
    1.09
    '__
    1.09
     relojes
    1.06
     ontvang
    1.02
    Ấ
    1.02
     remplacé
    1.02
    
    0.99
    Activations Density 0.032%

    No Known Activations