© 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. 107765
    Prev
    Next
    INDEX
    Explanations

    offering thanks and compliments

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

    This neuron fires on the very start of a direct quotation or formal speech segment (e.g., the opening of a quoted statement).

    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
     Majority
    -0.82
     offers
    -0.82
     offered
    -0.79
     extension
    -0.75
     offer
    -0.73
     offering
    -0.72
     угло
    -0.70
     instantly
    -0.69
     обладает
    -0.69
    Concurrency
    -0.67
    POSITIVE LOGITS
     sincere
    2.86
     deepest
    2.56
     sincer
    2.20
     heartfelt
    2.14
    incere
    2.11
     warmest
    1.98
     deep
    1.72
     sincero
    1.63
    deep
    1.51
     profonde
    1.51
    Activations Density 0.021%

    No Known Activations