© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60275
    Prev
    Next
    INDEX
    Explanations

    create object or process

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

    The neuron flags domain‐style identifier tokens—i.e. components of fully qualified names or URIs such as “com,” “org,” “xml,” “w3,” “example,” and similar namespace or package fragments.

    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
    DIPSETTING
    -0.88
    tojas
    -0.88
     тях
    -0.88
    юще
    -0.88
     konkuren
    -0.88
    verständlich
    -0.83
     maquilla
    -0.83
     pengantin
    -0.82
     žel
    -0.82
     asfalto
    -0.81
    POSITIVE LOGITS
    create
    1.02
    Create
    1.01
    FI
    0.96
     portal
    0.93
     process
    0.93
    Find
    0.93
     quote
    0.92
     request
    0.91
     create
    0.90
    Get
    0.90
    Activations Density 0.064%

    No Known Activations