© 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. 34-GEMMASCOPE-RES-131K
    7. 7244
    Prev
    Next
    INDEX
    Explanations

    username or handle

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

    The neuron fires on mentions of user or account identifiers—e.g. IDs, account names, profile handles, and related labels.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    okovic
    -0.82
    bulin
    -0.82
    ™
    -0.79
    nó
    -0.78
    短信
    -0.77
    плом
    -0.77
    NEWS
    -0.74
    ndarray
    -0.73
    Pietro
    -0.73
     ју
    -0.73
    POSITIVE LOGITS
     username
    3.92
    username
    3.06
     handle
    2.77
    Username
    2.52
     Username
    2.48
     usernames
    2.39
    handle
    2.39
     handles
    2.30
    用户名
    2.25
     Handle
    2.19
    Activations Density 0.067%

    No Known Activations