© 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. 90644
    Prev
    Next
    INDEX
    Explanations

    verbs ending in -ing

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     蒸
    -1.47
     sewage
    -1.28
     zeer
    -1.26
     sonra
    -1.22
     bragging
    -1.20
    <0xE0>
    -1.17
     yacht
    -1.16
    staa
    -1.16
    omyces
    -1.14
    TWA
    -1.13
    POSITIVE LOGITS
     was
    1.39
     نداره
    1.30
     entweder
    1.27
     veröffentlich
    1.23
     either
    1.13
     revisor
    1.13
    Figure
    1.12
     It
    1.11
    Ἢ
    1.09
     好き
    1.08
    Activations Density 0.034%

    No Known Activations