© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 73023
    Prev
    Next
    INDEX
    Explanations

    not faint, ordinary, or cheap

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

    This neuron fires on adjectives (including hyphenated compounds) that express mediocrity or lack of exceptionalism—words like “faint-hearted,” “ordinary,” “average,” and “easy.”

    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
     notes
    -1.25
     esimerkiksi
    -1.22
    持續
    -1.19
     lancia
    -1.18
     móg
    -1.15
     steigen
    -1.13
    ̀
    -1.13
     onPress
    -1.13
     ends
    -1.13
     לְ
    -1.13
    POSITIVE LOGITS
     dernière
    1.26
     nocturne
    1.16
     επίσης
    1.16
    而且
    1.15
    Unexpected
    1.15
     también
    1.13
    byshev
    1.12
    Unique
    1.12
     uniquement
    1.11
     nivel
    1.10
    Activations Density 0.020%

    No Known Activations