© 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. 22-GEMMASCOPE-RES-131K
    7. 67651
    Prev
    Next
    INDEX
    Explanations

    very helpful, efficient, professional

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

    This neuron activates on positive sentiment words—especially praising adjectives and intensifying adverbs—indicative of favorable opinions or reviews.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    vább
    -1.33
    breviations
    -1.32
    ícias
    -1.23
     for
    -1.21
     or
    -1.17
     now
    -1.16
     from
    -1.16
    orist
    -1.14
    なと
    -1.14
    −/−
    -1.12
    POSITIVE LOGITS
    也很
    1.55
    也非常
    1.19
     constamment
    1.16
    eurovision
    1.16
     professional
    1.13
     understanding
    1.13
    Histology
    1.10
     patient
    1.09
     น่า
    1.09
    vání
    1.07
    Activations Density 0.009%

    No Known Activations