© 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. 56015
    Prev
    Next
    INDEX
    Explanations

    compensation and claims

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

    The neuron spotlights formal institutional or legal entity names and document headings (e.g. commissions, offices, processes, and case identifiers).

    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
     contrato
    -0.95
     huur
    -0.92
     probation
    -0.85
    ALLENGE
    -0.84
     threats
    -0.82
    瘠
    -0.82
     delete
    -0.81
     Suicide
    -0.81
     suicide
    -0.81
    itonitis
    -0.80
    POSITIVE LOGITS
     compensation
    1.56
     victims
    1.53
     compensate
    1.44
     compens
    1.41
     claimants
    1.38
     compensating
    1.38
     Compensation
    1.35
     payments
    1.34
    Compensation
    1.31
    Repar
    1.26
    Activations Density 0.026%

    No Known Activations