© 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. 34-GEMMASCOPE-RES-131K
    7. 115698
    Prev
    Next
    INDEX
    Explanations

    words ending in -ing, -ed, -ifying

    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_34/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
    ент
    -0.80
    lemb
    -0.79
    Kali
    -0.79
     Kali
    -0.76
    iertes
    -0.74
    lamo
    -0.73
    렘
    -0.73
    濂
    -0.72
     Feather
    -0.71
     кой
    -0.71
    POSITIVE LOGITS
    ingly
    1.80
    ifying
    1.52
    izing
    1.47
    ising
    1.26
    ing
    1.24
     душу
    1.16
    fying
    1.16
    vating
    1.15
    ating
    1.12
    ING
    1.12
    Activations Density 0.028%

    No Known Activations