© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63354
    Prev
    Next
    INDEX
    Explanations

    website hosting paths

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

    The neuron fires on technical setup terms related to domain and FTP account configuration (e.g. “domain,” “login,” “FTP,” “cPanel”).

    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
    onatos
    -0.77
    Ṗ
    -0.76
     Mesin
    -0.73
     toothpick
    -0.71
     LMS
    -0.71
     urodz
    -0.71
     VBox
    -0.71
     insolvent
    -0.71
    Ко
    -0.70
    herd
    -0.70
    POSITIVE LOGITS
     domain
    0.93
    Emails
    0.81
    риди
    0.77
    Domains
    0.77
     domains
    0.76
    domain
    0.76
     maksi
    0.73
    Addon
    0.73
    Guided
    0.73
     email
    0.73
    Activations Density 0.035%

    No Known Activations