© 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. 127248
    Prev
    Next
    INDEX
    Explanations

    words ending in able

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

    The neuron selectively activates on words ending with the suffix “able,” i.e., adjectives (or participles) formed with “-able.”

    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
     [{
    -1.35
     "",
    -1.27
     occidentale
    -1.25
     ""
    -1.24
    anza
    -1.23
    駅の
    -1.20
     hiasan
    -1.19
    )
    -1.19
     primeros
    -1.18
    ANNELS
    -1.17
    POSITIVE LOGITS
     without
    1.32
     both
    1.27
    ↵
    1.27
     indietro
    1.21
     between
    1.16
     assolutamente
    1.14
     lontano
    1.13
     either
    1.10
     következő
    1.10
    我们的
    1.09
    Activations Density 0.165%

    No Known Activations