© 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. 77725
    Prev
    Next
    INDEX
    Explanations

    filling out forms

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

    The neuron detects passages instructing the reader to fill in or complete a form (e.g., “complete the form below,” “fill out our refund request form,” etc.).

    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
     completed
    -1.02
     Completed
    -0.96
    completed
    -0.95
    Completed
    -0.95
    픈
    -0.85
     COMPLETED
    -0.83
    settled
    -0.81
    Correo
    -0.77
    )_{\
    -0.74
    Herz
    -0.74
    POSITIVE LOGITS
     questionnaire
    1.29
     fields
    1.20
    Fields
    1.07
     singkat
    1.02
     questionnaires
    1.01
     details
    0.96
     Fields
    0.96
     brief
    0.90
     blanks
    0.89
     FIELDS
    0.89
    Activations Density 0.019%

    No Known Activations