© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 40680
    Prev
    Next
    INDEX
    Explanations

    billing and pricing plans

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

    The neuron detects terms related to service pricing and billing details—e.g. subscription plans, fees, expiration dates, quotas, and payment.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    But
    -1.65
     all
    -1.52
    However
    -1.44
     ourselves
    -1.43
    但
    -1.41
     traditionally
    -1.40
     family
    -1.37
     commonly
    -1.31
    If
    -1.30
    Since
    -1.30
    POSITIVE LOGITS
     illustratie
    1.47
     they
    1.40
     jejich
    1.38
     feminino
    1.37
     beleid
    1.33
    を目指す
    1.28
     diensten
    1.27
    滏
    1.24
     médicament
    1.24
     bedrijven
    1.23
    Activations Density 0.085%

    No Known Activations