© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49369
    Prev
    Next
    INDEX
    Explanations

    verbs ending in -ate, -ise, -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_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
     of
    -1.08
     इसे
    -0.92
     the
    -0.92
     them
    -0.91
    これを
    -0.88
     sitä
    -0.86
    разу
    -0.83
     ją
    -0.82
    把
    -0.81
    それを
    -0.79
    POSITIVE LOGITS
    ingin
    0.96
    cowboy
    0.88
    dicionado
    0.85
     човек
    0.85
    ating
    0.85
    izarse
    0.83
    嬅
    0.83
     lohnt
    0.82
    ować
    0.82
     کردن
    0.81
    Activations Density 0.063%

    No Known Activations