© 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. 10-GEMMASCOPE-RES-131K
    7. 65136
    Prev
    Next
    INDEX
    Explanations

    compound adjectives and nouns

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

    This neuron activates on mentions of touchscreen displays.

    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
     When
    -3.28
     当
    -2.67
     With
    -2.64
     The
    -2.44
     :
    -2.41
    皷
    -2.39
    ⚋
    -2.38
     {
    -2.25
    }
    -2.23
    攬
    -2.22
    POSITIVE LOGITS
    ஂ
    2.97
    Skocz
    2.81
    摃
    2.80
     để
    2.72
    玙
    2.72
    龊
    2.67
    神
    2.64
    will
    2.61
    ll
    2.59
    we
    2.56
    Activations Density 0.182%

    No Known Activations