© 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. 71611
    Prev
    Next
    INDEX
    Explanations

    user profile management

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

    The neuron fires on code identifiers and strings related to user profile or account management (e.g. “Profile,” “StoreProfileRequest,” page/controller names, and similar).

    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
    矣
    -1.10
     گر
    -1.02
    ぞれ
    -1.01
    miljø
    -0.95
     but
    -0.94
    eração
    -0.94
     geschaffen
    -0.93
     hinzugefügt
    -0.92
     aufgrund
    -0.91
    ptid
    -0.90
    POSITIVE LOGITS
    ynchronously
    1.34
     personal
    1.34
     changes
    1.25
     self
    1.25
     change
    1.25
    SELF
    1.22
     changing
    1.22
     autobio
    1.15
    Self
    1.15
     profile
    1.15
    Activations Density 0.014%

    No Known Activations