© 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. 4071
    Prev
    Next
    INDEX
    Explanations

    user activation and roles

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

    This neuron flags code identifiers—especially class/namespace names and variable names (e.g. CamelCase and underscored identifiers) in code snippets.

    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
    nect
    -0.81
    товая
    -0.76
    EmployeeId
    -0.76
    userLogin
    -0.75
     immers
    -0.75
    loginForm
    -0.74
    isAuth
    -0.74
     cận
    -0.74
    isLogin
    -0.73
    interpret
    -0.72
    POSITIVE LOGITS
     inactive
    1.53
     deactivate
    1.52
     role
    1.50
     activate
    1.47
     deactivated
    1.45
     roles
    1.44
     active
    1.44
     activation
    1.43
    Deacti
    1.35
     Role
    1.34
    Activations Density 0.050%

    No Known Activations