© 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. 108729
    Prev
    Next
    INDEX
    Explanations

    to infinitive verbs

    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
     armées
    -0.84
     vizsg
    -0.78
    ował
    -0.77
     képes
    -0.76
     Szene
    -0.76
    𝘬
    -0.74
     wykonane
    -0.72
    Hah
    -0.72
     apprécier
    -0.72
    Pry
    -0.71
    POSITIVE LOGITS
     to
    2.59
    ToBe
    1.27
     לה
    1.16
    ที่จะ
    1.04
    tobe
    1.02
     чтобы
    0.95
     để
    0.92
     لت
    0.91
    לה
    0.84
    toBe
    0.77
    Activations Density 0.042%

    No Known Activations