© 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. 30318
    Prev
    Next
    INDEX
    Explanations

    acknowledgement or acceptance

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

    This neuron detects references to bureaucratic or legal case/application status updates (e.g. filings, approvals, received correspondence, and current review status).

    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
    气质
    -0.78
     Pind
    -0.78
    reporting
    -0.75
     gön
    -0.73
    APPROVED
    -0.71
    Reporting
    -0.70
    发货
    -0.70
     Fired
    -0.69
     CONTRACT
    -0.69
     vực
    -0.69
    POSITIVE LOGITS
     assigned
    1.62
     acknowledged
    1.48
     acknowledgement
    1.44
     acknowledge
    1.41
     receipt
    1.39
     accepted
    1.35
     acknowledgment
    1.26
     received
    1.25
     acceptance
    1.24
     acknowledges
    1.20
    Activations Density 0.060%

    No Known Activations