© 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. 38232
    Prev
    Next
    INDEX
    Explanations

    positive qualities and treasures

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

    The neuron strongly activates on vivid, sensory or promotional descriptors (especially positive adjectives like “juicy,” “sweet,” “overflowing,” “awesome,” etc.) that embellish or hype up a noun.

    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
    rug
    -0.90
    зацию
    -0.88
    ﻰ
    -0.82
     пого
    -0.81
     ЕС
    -0.81
    ided
    -0.81
     penge
    -0.80
     ร
    -0.78
     DEFAULT
    -0.77
     jurisdictions
    -0.77
    POSITIVE LOGITS
     goodness
    4.31
     goodies
    2.92
     Goodness
    2.78
    Goodness
    2.33
     greatness
    2.30
     good
    1.88
    goo
    1.81
     goods
    1.80
     loveliness
    1.74
     treasures
    1.73
    Activations Density 0.069%

    No Known Activations