© 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. 48263
    Prev
    Next
    INDEX
    Explanations

    vehicle specs and capabilities

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

    The neuron fires on numeric values and quantitative measurements (e.g. stats, ratings, dimensions, and other specification numbers).

    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
     or
    -1.63
     about
    -1.47
     newOwner
    -1.35
     Haziran
    -1.30
    新的
    -1.24
    órica
    -1.23
     knew
    -1.21
     nogle
    -1.18
    ódios
    -1.18
    Mereka
    -1.17
    POSITIVE LOGITS
     you
    1.72
     képes
    1.27
     болезни
    1.20
     parvenir
    1.19
     pourront
    1.16
    💰
    1.15
    ありが
    1.13
    挪
    1.10
     parlant
    1.07
    发言
    1.06
    Activations Density 0.126%

    No Known Activations