© 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. 129353
    Prev
    Next
    INDEX
    Explanations

    transfer, amount, safe, Tomorrow

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

    The neuron fires on programming identifiers—especially function and contract names (e.g. CamelCase or capitalized tokens) in code.

    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
    k
    -1.59
    m
    -1.51
    v
    -1.50
    s
    -1.49
    ങ്ങള
    -1.45
    j
    -1.45
    il
    -1.44
    w
    -1.41
    …)
    -1.37
    ↵↵
    -1.35
    POSITIVE LOGITS
    ]
    1.60
    }
    1.58
    所謂
    1.57
    濕
    1.55
     gezicht
    1.54
    這個
    1.48
    所谓的
    1.48
    امین
    1.47
     zelve
    1.47
     without
    1.45
    Activations Density 0.001%

    No Known Activations